[ { "productId": "brex", "storyId": "24-7-support-access", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains no documentation or claims about live customer support availability, support channels, or response times for urgent account issues. Community evidence instead discusses account closures and rejections, which is unrelated to support-reliability as described in the story.", "evidenceIds": [] }, { "productId": "brex", "storyId": "accounting-software-sync", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Brex documents automated GL coding, accounting API, thousands of native integrations for syncing across finance tools, and one-click accrual booking to close books daily, directly supporting automated transaction/expense sync with accounting software. Missing for 10: named integrations with specific accounting platforms (e.g. QuickBooks/NetSuite) and independent hands-on verification of sync reliability.", "evidenceIds": [ "brex-docs-1", "brex-docs-8", "brex-docs-14", "brex-docs-17", "brex-docs-25", "brex-intdir-1" ] }, { "productId": "brex", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "A direct probe confirms Brex serves a proper llms.txt file at developer.brex.com/llms.txt (HTTP 200) with a structured table of contents pointing to agent-friendly docs, and Brex also documents an MCP server for agent interaction, reinforcing an agent-oriented docs strategy. Missing for 10: independent third-party confirmation of an agent actually consuming llms.txt successfully in practice.", "evidenceIds": [ "brex-probe-1", "brex-docs-21", "brex-probe-3" ] }, { "productId": "brex", "storyId": "agentic-ai-insights", "verdict": "disputed", "quality": 4, "confidence": "medium", "rationale": "Brex markets AI-powered features like an 'AI-powered expense assistant' and AI automation for invoices/GL coding, implying AI-generated insights from user financial data (brex-docs-7, brex-docs-16, brex-docs-9). However, hands-on community discussion of Brex's own AI chatbot demo reports concrete factual errors (bot miscounted/misdated receipts) and criticism that the underlying model is non-deterministic and unreliable for financial insight tasks, directly contradicting the polished vendor claims (brex-comm-1, brex-comm-4). Missing for 10: first-party documentation of a concrete insights/suggestions feature (e.g., dashboards with AI commentary), independent verification that current production AI features are accurate, and resolution of the hallucination concerns raised by the community.", "evidenceIds": [ "brex-docs-7", "brex-docs-16", "brex-docs-9", "brex-comm-1", "brex-comm-4" ] }, { "productId": "brex", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex documents several automation building blocks that can run without manual triggering — auto-enforced budget controls, AI-powered invoice entry/approval/payment automation, automated GL coding/accruals, a Webhooks API for real-time event-driven triggers, and third-party workflow automation via Pipedream/Zapier (e.g., bulk card issuance, scheduled CSV exports) — which together let an AI-native user configure background automations. However, there is no first-party 'agent scheduler' or persistent autonomous-agent runtime; the MCP server (brex-docs-21) is framed as an interactive assistant interface rather than an autonomous background job runner. Missing for 10: a dedicated autonomous-agent/scheduling feature explicitly designed for unattended multi-step AI workflows, and independent confirmation that these automations run reliably without human oversight.", "evidenceIds": [ "brex-docs-3", "brex-docs-6", "brex-docs-7", "brex-docs-8", "brex-docs-14", "brex-docs-23", "brex-docs-24", "brex-docs-28", "brex-docs-21" ] }, { "productId": "brex", "storyId": "agentic-builtin-assistant", "verdict": "disputed", "quality": 5, "confidence": "medium", "rationale": "Brex documents an 'AI-powered expense assistant' and AI-driven automation for invoice/GL coding (brex-docs-16, brex-docs-7, brex-docs-9), suggesting a built-in assistant users can delegate tasks to. However, hands-on community discussion of Brex's own AI demo reports factual errors in the assistant's output (misidentifying the most recent receipt date) and skepticism about using a non-deterministic model for production financial tasks (brex-comm-1, brex-comm-2, brex-comm-4), directly contradicting reliability claims. Missing for 10: independent corroboration of the assistant working correctly in production, clear scope/limits of what tasks can be delegated, and resolution of the reported output error.", "evidenceIds": [ "brex-docs-16", "brex-docs-7", "brex-docs-9", "brex-comm-1", "brex-comm-2", "brex-comm-4" ] }, { "productId": "brex", "storyId": "agentic-headless", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Brex exposes REST APIs (Accounting, Payments, Transactions, Team, Webhooks) and webhooks that can be scripted/automated outside a UI, which supports headless/CI-style automation, and Postman/Pipedream/Zapier integration docs further show programmatic, non-interactive usage patterns. However, there is no explicit documentation of a CLI, SDK, service-account/API-key auth flow for CI pipelines, or any first-party guidance on running Brex workflows in automated/headless CI environments. missing for 10: explicit CI/headless automation guidance, CLI or SDK for scripting, service-account/token auth documentation for non-interactive use, independent confirmation of CI usage.", "evidenceIds": [ "brex-docs-1", "brex-docs-4", "brex-docs-3", "brex-docs-12", "brex-docs-13", "brex-docs-22", "brex-docs-23", "brex-docs-24", "brex-probe-1" ] }, { "productId": "brex", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows Brex publishes its own MCP server so external AI assistants can call Brex's tools (brex-docs-21, brex-probe-3) — this is the opposite direction from the story, which asks whether Brex itself can plug in and consume external MCP servers as a client. No evidence exists of Brex acting as an MCP client or letting users attach third-party MCP servers for it to use.", "evidenceIds": [ "brex-docs-21", "brex-probe-3" ] }, { "productId": "brex", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Brex documents an official MCP server (developer.brex.com/docs/mcp) that lets AI assistants manage expenses, look up users, check cards, review transactions, and track bills via natural language, confirmed by both docs and a probe. Missing for 10: independent hands-on community corroboration of the MCP server itself (community evidence found is unrelated to MCP) and details on auth/security model.", "evidenceIds": [ "brex-docs-21", "brex-probe-3" ] }, { "productId": "brex", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex documents an official MCP server that lets AI assistants manage expenses, look up users, check cards, and review transactions 'through natural language,' directly enabling natural-language operation of the product (brex-docs-21, brex-probe-3). However, there's no independent hands-on validation of the MCP server's reliability, and older community commentary raises general skepticism about non-deterministic AI outputs in Brex's financial workflows (brex-comm-1–4), though this pertains to a separate legacy AI feature rather than the MCP server itself. Missing for 10: independent/hands-on corroboration of the MCP server's natural-language commands working reliably in practice, and broader documentation of natural-language support beyond the MCP feature.", "evidenceIds": [ "brex-docs-21", "brex-probe-3", "brex-comm-1" ] }, { "productId": "brex", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of an official Brex CLI tool; developer docs mention APIs, Postman, Pipedream, Zapier, and an MCP server, but no CLI is documented.", "evidenceIds": [] }, { "productId": "brex", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Brex has an extensive documented public API surface (Accounting, Budgets, Webhooks, Team, Expenses, Payments, Transactions, Onboarding, Travel) with a quickstart guide, llms.txt discovery, Postman support, and even an MCP server for AI-native agentic access, giving strong evidence AI-native users can drive Brex programmatically. missing for 10: no live/verified OpenAPI spec (candidate URLs returned 404), and no independent third-party corroboration of API robustness beyond vendor docs.", "evidenceIds": [ "brex-docs-5", "brex-docs-1", "brex-docs-2", "brex-docs-3", "brex-docs-4", "brex-docs-11", "brex-docs-12", "brex-docs-13", "brex-docs-18", "brex-docs-19", "brex-docs-20", "brex-docs-21", "brex-docs-22", "brex-probe-1", "brex-probe-3", "brex-probe-2" ] }, { "productId": "brex", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Brex documents many separate API modules (Accounting, Budgets, Team, Payments, etc.) and an MCP server for AI assistants, but there is no evidence of a mechanism to issue scoped or least-privilege API credentials/tokens specifically for an agent (e.g., OAuth scopes, granular API-key permissions, or agent-specific credential issuance).", "evidenceIds": [ "brex-docs-1", "brex-docs-2", "brex-docs-4", "brex-docs-21", "brex-probe-3" ] }, { "productId": "brex", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows extensive REST API documentation (Accounting, Budgets, Team, Payments, Transactions, etc.), a quickstart guide, Postman collection, and third-party low-code integrations (Pipedream, Zapier), but no mention anywhere of official client SDKs (e.g., Python/JS/Go libraries). A probe for an OpenAPI spec that could underpin SDK generation also returned 404s across all candidate paths, suggesting no discoverable machine-readable spec for SDK tooling.", "evidenceIds": [ "brex-docs-1", "brex-docs-5", "brex-docs-22", "brex-probe-2" ] }, { "productId": "brex", "storyId": "agentic-webhooks", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Brex has a dedicated Webhooks API with first-party docs explicitly describing real-time event notifications for account activity, directly matching the story. Missing for 10: independent/hands-on developer corroboration of webhook reliability and no evidence of event-type coverage breadth or payload examples.", "evidenceIds": [ "brex-docs-3", "brex-docs-20" ] }, { "productId": "brex", "storyId": "ai-anomaly-spend-detection", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows rule-based auto-enforced budget controls (brex-docs-6) and a general AI-powered expense assistant (brex-docs-16), but nothing describes AI automatically detecting or flagging anomalous/out-of-policy transactions for review. Community threads discuss AI reliability concerns generally but don't confirm or deny this specific capability.", "evidenceIds": [ "brex-docs-6", "brex-docs-16", "brex-docs-7" ] }, { "productId": "brex", "storyId": "ai-bill-data-extraction", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex explicitly markets 'AI-powered automation of invoice entry, approval, and payments' and bill pay as part of its unified spend platform, and the MCP server lets AI assistants 'track bills' via natural language, suggesting AI can ingest and populate bill data for review. However, there's no detailed documentation of the specific workflow (OCR/reading incoming bills, field extraction, human-in-loop review step), and general community skepticism about AI reliability in financial workflows (hallucinated/missed expenses) raises caution about accuracy, though not a concrete dispute of the bill-pay feature itself. Missing for 10: explicit documentation of bill-reading/OCR extraction pipeline, a described human-review UI step, and independent verification of accuracy for auto-populated payment details.", "evidenceIds": [ "brex-docs-7", "brex-docs-26", "brex-docs-21", "brex-comm-1" ] }, { "productId": "brex", "storyId": "ai-books-close-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex explicitly documents AI-driven automations aimed at faster month-end close — one-click accrual booking, automated GL coding by entity, AI-powered invoice entry/approval, plus an Accounting API and MCP server for programmatic/AI-assisted access to accounting data. This directly matches the ai-native 'close books faster' story via first-party product documentation. missing for 10: independent/hands-on corroboration that these automations measurably speed up close, no case study or third-party validation of close-time reduction.", "evidenceIds": [ "brex-docs-14", "brex-docs-7", "brex-docs-8", "brex-docs-1", "brex-docs-21", "brex-docs-9" ] }, { "productId": "brex", "storyId": "ai-contract-parsing-procurement", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any vendor contract parsing or AI auto-population of procurement request forms; Brex's AI features cover expense assistant, invoice entry automation, and MCP-based account queries, not contract parsing for procurement. Missing for 10: any contract-ingestion/parsing feature, procurement form auto-population, or vendor document extraction capability.", "evidenceIds": [ "brex-docs-7", "brex-docs-15", "brex-docs-21" ] }, { "productId": "brex", "storyId": "ai-gl-coding-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex's own marketing explicitly claims automated GL coding by entity globally with one-click accrual booking to close books daily, directly matching the story (brex-docs-8, brex-docs-14), backed by an Accounting API for managing accounting data across entities (brex-docs-1) and AI-powered automation messaging (brex-docs-7, brex-docs-9). Missing for 10: independent/hands-on verification of GL-coding accuracy across entities and no third-party case study confirming close-acceleration outcomes.", "evidenceIds": [ "brex-docs-8", "brex-docs-14", "brex-docs-1", "brex-docs-7", "brex-docs-9" ] }, { "productId": "brex", "storyId": "ai-price-monitoring-rebooking", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Brex offers a Travel API to view trips and in-app travel bookings/itinerary changes, but there is no evidence of automated rate monitoring or automatic rebooking when prices drop; missing for 10: any documentation of price-drop monitoring, automated rebooking logic, or related travel-rate alert feature.", "evidenceIds": [ "brex-docs-16", "brex-docs-19" ] }, { "productId": "brex", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Brex publishes extensive API reference docs (Accounting, Budgets, Team, Webhooks, etc.) and a quickstart guide, and explicitly integrates with Postman so developers can 'test and play around with API calls without having to write code' (brex-docs-22, brex-docs-5). However, a probe found no OpenAPI/Swagger spec at standard endpoints (all 404s), indicating no confirmed built-in interactive/runnable API explorer on the docs site itself—Postman is an external tool rather than embedded runnable examples. Missing for 10: a native in-browser interactive API console with runnable code samples, and independent confirmation of an OpenAPI spec powering such a reference.", "evidenceIds": [ "brex-docs-5", "brex-docs-22", "brex-probe-2", "brex-probe-1" ] }, { "productId": "brex", "storyId": "api-machine-spec", "verdict": "disputed", "quality": 3, "confidence": "medium", "rationale": "Brex's docs reference an 'openapi' URL structure (e.g. developer.brex.com/openapi/webhooks_api.md) implying spec-based documentation, but a direct probe for standard machine-readable spec files (openapi.json, swagger.json, etc.) returned 404 on all candidate paths, meaning no downloadable OpenAPI spec is actually accessible. missing for 10: a working link to a downloadable OpenAPI/Swagger JSON or YAML file, confirmation that the 'openapi' folder pages are anything more than rendered markdown docs.", "evidenceIds": [ "brex-docs-20", "brex-probe-1", "brex-probe-2" ] }, { "productId": "brex", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No mention of a sandbox, test environment, or non-production mode anywhere in Brex's developer docs, API listings, or MCP server description; Postman usage is for testing API calls but against real accounts, not a sandbox. Missing for 10: any documented sandbox/test environment, test API keys, or separation from production data.", "evidenceIds": [ "brex-docs-22", "brex-docs-21", "brex-probe-1" ] }, { "productId": "brex", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack lists numerous Brex APIs and developer docs but nowhere mentions API versioning schemes or a documented deprecation policy; the OpenAPI spec probe even returned 404s, suggesting limited machine-readable API documentation.", "evidenceIds": [ "brex-probe-2", "brex-docs-1", "brex-docs-5" ] }, { "productId": "brex", "storyId": "application-status-tracking", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of an application-status tracking feature for founders during onboarding review; the Onboarding API only covers referral/prefill signup, and community threads discuss rejections/closures but not a status-check capability.", "evidenceIds": [] }, { "productId": "brex", "storyId": "auto-cash-topup-alerts", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack covers Brex's cards, expenses, budgets, payments, and webhooks APIs but contains no mention of auto top-up between accounts or low-balance alert functionality, which is a fair capability to expect from a business banking/treasury platform. Missing for 10: any documentation of auto-transfer/sweep rules between accounts, low-balance threshold alerts, or treasury automation features.", "evidenceIds": [ "brex-docs-10", "brex-docs-13", "brex-docs-20" ] }, { "productId": "brex", "storyId": "auto-receipt-capture-on-swipe", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex's docs describe automated receipt capture/matching (Expenses API 'receipt match and receipt uploads', 'automated receipts' in the expense assistant) and automatic GL coding by entity at close, matching the story of capture+coding without manual entry. missing for 10: independent/hands-on confirmation that receipts are captured at the exact moment of swipe with no manual step, and clearer documentation of the automation trigger mechanism.", "evidenceIds": [ "brex-docs-11", "brex-docs-16", "brex-docs-8", "brex-docs-14" ] }, { "productId": "brex", "storyId": "automatic-invoice-followup", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Brex is a corporate-card and spend-management platform focused on accounts-payable (bill pay, vendor payments, expense automation) — all evidence (brex-docs-7, brex-docs-12, brex-docs-14) is about paying vendors, not collecting from customers. Automated dunning/follow-up on overdue receivables is an accounts-receivable capability outside Brex's product category, so this axis does not apply.", "evidenceIds": [ "brex-docs-7", "brex-docs-12", "brex-docs-14" ] }, { "productId": "brex", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex documents bulk-style automation primarily through its Pipedream integration, explicitly citing 'bulk creating users, setting monthly limits for users, issuing virtual cards, and sending vendor payments,' and its API surface (Team, Payments, Budgets, Expenses) could support scripted multi-item operations. However, this relies on a third-party low-code platform rather than native bulk endpoints in Brex's own API docs, and there's no probe evidence of a bulk API or batch endpoint in the OpenAPI spec (which 404s). Missing for 10: native/first-party bulk API endpoints, documented batch limits, and independent verification of at-scale bulk operations.", "evidenceIds": [ "brex-docs-23", "brex-docs-4", "brex-docs-12", "brex-docs-2", "brex-probe-2" ] }, { "productId": "brex", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Brex has a Webhooks API for event notifications and Budgets API for auto-enforced spend controls, plus Pipedream/Zapier integrations that can chain actions on events, but these require external low-code platforms rather than a native rules engine where users directly define 'if event X then action Y' automations. missing for 10: a native rule-builder/automation engine within Brex itself, documented conditional trigger-action syntax, and independent confirmation that webhook+action chains work reliably in production.", "evidenceIds": [ "brex-docs-20", "brex-docs-6", "brex-docs-23", "brex-docs-24", "brex-docs-28" ] }, { "productId": "brex", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Brex has no native cron/scheduling API, but its documented Zapier example ('Monthly Export of Brex Card Transactions to CSV in Google Drive') and Pipedream integration examples imply recurring automated workflows can be built via third-party low-code platforms rather than Brex itself. Missing for 10: a first-party scheduler or recurring-job API, and any evidence of AI-native (MCP/agent) triggered recurring workflows.", "evidenceIds": [ "brex-docs-23", "brex-docs-24", "brex-docs-28", "brex-docs-25" ] }, { "productId": "brex", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any versioning, review, or rollback mechanism for automations/workflows (e.g., budget rules, approval flows, or webhook configs) — evidence only covers APIs, integrations, and general automation features without any change-history, audit-diff, or rollback capability.", "evidenceIds": [] }, { "productId": "brex", "storyId": "bank-verification-letter", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence pack shows Transactions/Accounting APIs for viewing accounts and statements, but nothing about viewing account/routing numbers or generating a bank verification letter is documented anywhere in the docs or community evidence.", "evidenceIds": [ "brex-docs-13", "brex-docs-1" ] }, { "productId": "brex", "storyId": "bill-pay-approval-workflow", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex explicitly advertises AI-powered invoice entry, approval, and payment automation (bill pay) plus vendor payments via Payments API and procurement approval flows on cards, supporting the core of the story. However, evidence lacks detail on an explicit bill-upload UI/OCR workflow or configurable multi-step approval chains before vendor payment, and community threads raise concerns about AI reliability in financial workflows (though not a direct dispute of this specific bill-approval feature). Missing for 10: detailed documentation of bill upload/OCR ingestion, explicit multi-tier approval routing configuration, and independent hands-on validation of the bill-pay approval flow.", "evidenceIds": [ "brex-docs-7", "brex-docs-12", "brex-docs-15", "brex-docs-26", "brex-comm-1" ] }, { "productId": "brex", "storyId": "budget-based-spend-enforcement", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex explicitly markets budgets with auto-enforced spend limits (brex-docs-6) and offers a dedicated Budgets API for managing budgets and budget programs (brex-docs-2), plus Team API for department/user structuring (brex-docs-4). Missing for 10: independent/hands-on verification of enforcement behavior and no detailed docs excerpt showing department-level scoping specifics beyond marketing copy.", "evidenceIds": [ "brex-docs-6", "brex-docs-2", "brex-docs-4" ] }, { "productId": "brex", "storyId": "card-spend-limits-controls", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex explicitly advertises budgets and per-transaction/per-card spend limits with auto-enforced controls (brex-docs-6, brex-docs-15) and exposes a Budgets API and Team API for managing users, departments, and cards (brex-docs-2, brex-docs-4), directly matching the finance-lead's need for granular per-employee card controls. missing for 10: independent/hands-on verification of the granularity of controls in practice and no dedicated documentation excerpt detailing exact limit types (e.g., merchant category, time-based) beyond marketing copy.", "evidenceIds": [ "brex-docs-6", "brex-docs-15", "brex-docs-2", "brex-docs-4" ] }, { "productId": "brex", "storyId": "consolidate-point-solutions", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex explicitly markets itself as a unified spend platform combining cards, banking, expense management, bill pay, accounting, and travel booking, directly matching the founder's need to consolidate point solutions (brex-docs-26, brex-docs-27, brex-docs-7, brex-docs-15, brex-docs-16). Rich API and integration documentation (Accounting, Payments, Expenses, Team, Travel APIs) supports this being a functioning single platform rather than marketing-only claims.\n\nmissing for 10: independent/hands-on case studies confirming founders actually consolidated multiple tools onto Brex, and no third-party corroboration of the 'fully unified' claim beyond vendor docs.", "evidenceIds": [ "brex-docs-26", "brex-docs-27", "brex-docs-7", "brex-docs-15", "brex-docs-16", "brex-docs-1", "brex-docs-11", "brex-docs-12", "brex-docs-17" ] }, { "productId": "brex", "storyId": "dedicated-accounting-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Brex documents a dedicated Accounting API ('View and manage accounting data') alongside related APIs (Expenses, Transactions, Payments), and the developer docs are confirmed live via probe. Missing for 10: independent/hands-on corroboration of the Accounting API's functionality and a discoverable OpenAPI schema (404s on standard paths).", "evidenceIds": [ "brex-docs-1", "brex-docs-11", "brex-docs-13", "brex-probe-1", "brex-probe-2" ] }, { "productId": "brex", "storyId": "earn-yield-on-balances", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Brex's marketing explicitly advertises 'up to 3.70%' yield on funds held directly in a Brex business account, indicating cash held with Brex (not moved to a separate institution) can earn yield. However, evidence is limited to a single marketing line with no detail on mechanism, eligibility, or independent verification. Missing for 10: documentation on how yield is generated (program banks/money-market sweep), terms/limits, and independent/hands-on confirmation of the yield actually being credited.", "evidenceIds": [ "brex-docs-10" ] }, { "productId": "brex", "storyId": "embedded-banking-no-license", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Brex's developer APIs (Team, Payments, Transactions, Onboarding) are for managing a company's own Brex account or referring customers to sign up for Brex directly — there is no evidence of a BaaS/embedded-banking program letting developers white-label bank accounts for their own end customers without a license. The Onboarding API only prefills signup info for referrals, not embedded account issuance.", "evidenceIds": [ "brex-docs-18", "brex-docs-4", "brex-docs-13", "brex-docs-26" ] }, { "productId": "brex", "storyId": "fast-cross-border-transfer", "verdict": "partial", "quality": 2, "confidence": "low", "rationale": "Brex markets 'fast global payments' and operations in 120+ countries, and its Payments API sends ACH/domestic wires/checks, but there is no documentation of international wire speed or any sub-minute delivery guarantee for cross-border transfers. missing for 10: explicit international/cross-border payment speed SLA, documentation of same-day or instant global wire capability, independent confirmation of transfer times.", "evidenceIds": [ "brex-docs-10", "brex-docs-27", "brex-docs-12" ] }, { "productId": "brex", "storyId": "fast-onboarding-switch", "verdict": "disputed", "quality": 3, "confidence": "medium", "rationale": "Brex offers an Onboarding API and quickstart docs implying fast signup (brex-docs-18, brex-docs-5), but multiple firsthand founder accounts describe painful, rejected, or abruptly terminated onboarding—requiring $1MM minimum balances for non-VC-backed startups, multi-attempt rejections, and being told to leave with 6 weeks notice—directly contradicting a quick, smooth week-long onboarding experience. missing for 10: any documented end-to-end onboarding timeline, first-party case studies showing 'week not months' onboarding, and resolution of the negative hands-on reports.", "evidenceIds": [ "brex-docs-18", "brex-docs-5", "brex-comm-8", "brex-comm-9", "brex-comm-10", "brex-comm-13", "brex-comm-14", "brex-comm-15", "brex-comm-16" ] }, { "productId": "brex", "storyId": "fdic-insurance-sweep", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions FDIC sweep networks or multi-bank deposit insurance maximization; Brex's documentation covers cards, expenses, APIs, and integrations but nothing about deposit sweep programs.", "evidenceIds": [] }, { "productId": "brex", "storyId": "fee-free-foreign-card-spend", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Brex advertises global corporate cards and banking usable in 120+ countries with fast global payments, implying international spend capability, but there is no explicit claim of zero foreign transaction fees or fee-free cash withdrawals abroad. Missing for 10: explicit no-foreign-transaction-fee policy, ATM/cash withdrawal terms abroad, and independent confirmation of fee-free international spend.", "evidenceIds": [ "brex-docs-27", "brex-docs-10", "brex-docs-26" ] }, { "productId": "brex", "storyId": "freeze-replace-card", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack mentions a Team API that can 'manage users, locations, departments, and cards' but never describes freezing a lost/stolen card or ordering a replacement. No docs, community, or probe evidence confirms this specific capability. Missing for 10: explicit documentation or UI/API evidence of card freeze and replacement ordering workflow.", "evidenceIds": [ "brex-docs-4" ] }, { "productId": "brex", "storyId": "gl-sync-erp", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex documents an Accounting API for viewing/managing accounting data, a Webhooks API for real-time event notifications, automated GL coding by entity, and 'automatic syncing across 1,000s of native integrations' spanning card swipe to month-end close — together implying near-real-time sync that reduces manual journal entry work. However, there is no explicit mention of named ERP systems (e.g., NetSuite, Sage Intacct) or confirmation that sync is truly bidirectional (push AND pull) rather than one-way export/webhook notification, and no independent/hands-on validation of ERP sync reliability. Missing for 10: named major ERP integration specifics, explicit bidirectional sync confirmation, and third-party corroboration of real-time accuracy.", "evidenceIds": [ "brex-docs-1", "brex-docs-3", "brex-docs-14", "brex-docs-25", "brex-intdir-1", "brex-docs-20" ] }, { "productId": "brex", "storyId": "high-yield-savings-subaccount", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence shows Brex offers a yield on cash (\"Unlock up to 3.70%\") but there is no mention of a distinct high-yield savings sub-account or of automated transfer rules to move cash into/out of such a sub-account.", "evidenceIds": [ "brex-docs-10" ] }, { "productId": "brex", "storyId": "instant-virtual-card-issuance", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Vendor docs explicitly describe issuing vendor-specific virtual cards with per-transaction limits and procurement approval flows, plus budget-based auto-enforced spend limits and a Team API to manage cards, directly matching the story; a Pipedream example even shows programmatic virtual card creation for a recurring stipend use case. However, all evidence is vendor-authored with no independent/hands-on confirmation of speed ('instantly') or real-world reliability of the scoping controls. Missing for 10: independent or hands-on verification of instant card creation and real customer confirmation of vendor/purpose-scoped limits working as described.", "evidenceIds": [ "brex-docs-15", "brex-docs-6", "brex-docs-4", "brex-docs-28", "brex-docs-2" ] }, { "productId": "brex", "storyId": "invoice-creation-collection", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Brex's evidence covers cards, expenses, bill pay, budgets, payments (ACH/wires/checks to vendors), and accounting integrations, but there is no mention of creating or sending branded customer-facing invoices with payment collection (i.e., accounts-receivable invoicing) anywhere in the docs or APIs listed.", "evidenceIds": [] }, { "productId": "brex", "storyId": "lock-exchange-rate", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions FX rate locking or forward-rate contracts; Brex's documented capabilities cover payments, expenses, cards, and integrations but not currency rate lock windows for transfers.", "evidenceIds": [] }, { "productId": "brex", "storyId": "multi-currency-account-creation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows global card/banking reach in 120+ countries and fast global payments, but nothing describes holding or managing balances in multiple currencies within a single account. Missing for 10: any explicit multi-currency wallet/balance feature, FX conversion mechanics, or account structure supporting simultaneous currency balances.", "evidenceIds": [ "brex-docs-10", "brex-docs-27" ] }, { "productId": "brex", "storyId": "multi-currency-interest", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Brex advertises up to 3.70% yield on cash balances (brex-docs-10), but there is no evidence of interest being earned specifically on balances held in multiple currencies—Brex's offering appears to be a single (USD) yield-bearing cash account with no multi-currency treasury/interest feature documented.", "evidenceIds": [ "brex-docs-10" ] }, { "productId": "brex", "storyId": "multiple-checking-subaccounts", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence in the pack of Brex offering multiple checking sub-accounts or auto-allocation of incoming deposits across them; docs cover budgets, expenses, payments, and integrations but nothing about sub-account structuring or deposit-splitting rules.", "evidenceIds": [] }, { "productId": "brex", "storyId": "no-fee-card-cashback", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Brex marketing mentions cash back as a benefit of the business account, implying it accrues on spend, but there is no documentation describing the mechanism, whether it is automatic, or that no redemption step is required. missing for 10: details on automatic accrual process, redemption mechanics, any confirmation that no manual steps are needed, independent corroboration.", "evidenceIds": [ "brex-docs-10" ] }, { "productId": "brex", "storyId": "one-click-payment-approval", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Evidence shows Brex has bill-pay/invoice approval automation (brex-docs-7), vendor payment sending via Payments API (brex-docs-12), and procurement approval flows for cards (brex-docs-15), implying approval workflows exist, but there is no direct documentation of configuring designated-teammate approval permissions or a one-click approve-and-send payment action for a finance-lead. Missing for 10: explicit docs on setting approval roles/permissions, evidence of a one-click approve-and-send UX, and independent confirmation this works as described.", "evidenceIds": [ "brex-docs-7", "brex-docs-12", "brex-docs-15", "brex-docs-4" ] }, { "productId": "brex", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex documents a broad first-party API surface (accounting, budgets, team, expenses, payments, transactions, travel, onboarding, webhooks) covering most core UI workflows, plus an MCP server for natural-language access, suggesting strong but not confirmed full parity. There is no explicit vendor claim of 1:1 UI/API parity, no independent corroboration that every UI action is API-accessible, and a probe for a public OpenAPI spec returned 404s, limiting verifiability. Missing for 10: explicit parity statement, independent verification of completeness, discoverable OpenAPI schema.", "evidenceIds": [ "brex-docs-1", "brex-docs-2", "brex-docs-3", "brex-docs-4", "brex-docs-11", "brex-docs-12", "brex-docs-13", "brex-docs-18", "brex-docs-19", "brex-docs-21", "brex-probe-2" ] }, { "productId": "brex", "storyId": "openness-full-export", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Brex exposes Transactions, Expenses, Accounting, and Team APIs that let users pull data out programmatically, and a documented Zapier example shows exporting card transactions to CSV — both are open, non-proprietary formats. However, there is no documented single 'export everything and leave' feature, no full account-data portability/archive tool, and community threads describe abrupt account closures with no mention of a clean data-export path. Missing for 10: a dedicated full-account data export/portability feature, confirmation that all data categories (not just transactions/expenses) are exportable, and independent evidence of successful full data migration on account closure.", "evidenceIds": [ "brex-docs-11", "brex-docs-13", "brex-docs-1", "brex-docs-24", "brex-comm-14" ] }, { "productId": "brex", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Brex is a closed proprietary fintech SaaS platform, not open-source software; source code availability under an open license is a category error for this kind of product.", "evidenceIds": [] }, { "productId": "brex", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Brex is a fintech/SaaS financial operations platform (cards, banking, expenses); self-hosting is a category error for a hosted financial services product, not an applicable axis.", "evidenceIds": [] }, { "productId": "brex", "storyId": "physical-card-issuance", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex's Team API explicitly manages users, departments, and cards, and marketing docs describe issuing vendor/team-specific cards with per-transaction limits and budget-based spend controls, supporting role-based card issuance. However, evidence never explicitly confirms physical (vs. virtual-only) card issuance or details role/permission granularity for card assignment. missing for 10: explicit mention of physical card issuance, detailed role-based permission model, independent corroboration of the physical card program.", "evidenceIds": [ "brex-docs-4", "brex-docs-15", "brex-docs-6", "brex-docs-26" ] }, { "productId": "brex", "storyId": "po-matched-invoice-automation", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Brex documents AI-powered invoice entry automation, automated GL coding by entity, and payment/vendor APIs (brex-docs-7, brex-docs-8, brex-docs-14, brex-docs-12), which covers invoice coding and routing for payment. However, there is no evidence of purchase-order matching or three-way match capability anywhere in the pack. Missing for 10: explicit PO-to-invoice matching functionality, documentation of approval routing workflow details, and independent/hands-on corroboration of the AI invoice automation working reliably.", "evidenceIds": [ "brex-docs-7", "brex-docs-8", "brex-docs-14", "brex-docs-12", "brex-docs-15" ] }, { "productId": "brex", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions data residency, regional storage options, or geographic controls for where Brex stores customer data; all docs focus on APIs, integrations, and product features. Missing for 10: any documentation of region/residency selection, data center locations, or compliance certifications tied to data storage location.", "evidenceIds": [] }, { "productId": "brex", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item addresses AI training data usage, opt-out controls, or data-privacy policy regarding model training; all docs cover APIs, integrations, and MCP functionality, not privacy posture toward AI training.", "evidenceIds": [] }, { "productId": "brex", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items address data retention, deletion controls, or privacy/data lifecycle policies for AI-native usage (e.g., MCP server or API data handling); the docs cover API capabilities and integrations but nothing about controlling or deleting stored data.", "evidenceIds": [] }, { "productId": "brex", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses telemetry/usage-tracking opt-out settings for AI-native workflows or the MCP server; the docs cover APIs, integrations, and product features but nothing about privacy/telemetry controls.", "evidenceIds": [] }, { "productId": "brex", "storyId": "receipt-matching-by-email-upload", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Brex's docs mention 'automated receipts' and an Expenses API with 'receipt match and receipt uploads', supporting automatic attachment of uploaded receipts to transactions, but there is no explicit mention of emailing receipts in or independent hands-on confirmation of the matching accuracy. Missing for 10: explicit email-to-receipt ingestion documentation, and independent verification that auto-matching works reliably.", "evidenceIds": [ "brex-docs-11", "brex-docs-16" ] }, { "productId": "brex", "storyId": "receive-multi-currency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Brex evidence covers corporate cards, spend management, and outbound payments (ACH, wires, checks via the Payments API) but contains no mention of receiving payments via local account details in multiple currencies (e.g., local IBAN/account numbers for USD, EUR, GBP, etc.). The 'fast global payments' and '120+ countries' claims refer to outbound/global card acceptance, not local receiving accounts.", "evidenceIds": [ "brex-docs-12", "brex-docs-10", "brex-docs-27" ] }, { "productId": "brex", "storyId": "request-limit-increase", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence shows budgets/spend-limit setting and per-transaction limits for cards (brex-docs-6, brex-docs-15) but no mention of a self-service screen for requesting a transaction limit increase or an approval workflow for such requests.", "evidenceIds": [ "brex-docs-6", "brex-docs-15", "brex-docs-2" ] }, { "productId": "brex", "storyId": "role-based-permissions", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Brex's Team API explicitly manages 'users, locations, departments, and cards,' suggesting structural support for organizing teams by location/department, and Budgets API allows spend controls tied to programs/teams. However, no evidence details specific role definitions (e.g., admin, bookkeeper, approver), permission granularity, or an admin console for configuring access levels. Missing for 10: explicit role/permission documentation, UI screenshots of role management, and independent confirmation of granular access control enforcement.", "evidenceIds": [ "brex-docs-4", "brex-docs-2", "brex-docs-15" ] }, { "productId": "brex", "storyId": "send-domestic-ach-wire", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Brex's Payments API documentation explicitly states it can 'Manage vendors and send ACH, domestic wires, and checks,' and marketing material references bill pay/invoice payment automation, directly matching the finance-lead story of sending domestic ACH and wire payments to vendors. Missing for 10: independent/hands-on verification of successful payment execution and more detail on approval workflows or transaction limits.", "evidenceIds": [ "brex-docs-12", "brex-docs-26", "brex-docs-7", "brex-docs-14" ] }, { "productId": "brex", "storyId": "send-international-payments", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Brex references 'fast global payments' and operations 'in 120+ countries,' and its Payments API supports ACH, domestic wires, and checks, but there is no documentation of sending international payments in local currencies or of transparent/disclosed FX fees. Missing for 10: explicit local-currency international payment support, FX conversion mechanics, and transparent fee disclosure/pricing documentation.", "evidenceIds": [ "brex-docs-10", "brex-docs-27", "brex-docs-12" ] }, { "productId": "brex", "storyId": "transfer-delivery-estimate", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Brex's Payments API supports sending ACH, wires, and checks, but no evidence shows a delivery-estimate or ETA feature surfaced to finance leads before confirming a transfer; missing for 10: any documentation of delivery-time estimates, confirmation UI, or timing guarantees for ACH/wire payments.", "evidenceIds": [ "brex-docs-12" ] }, { "productId": "brex", "storyId": "universal-transaction-search", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack documents separate APIs (Transactions, Payments, Expenses, Team) and integrations, but nowhere describes a unified 'universal search bar' UI that lets a finance-lead search transactions, vendors, and cards together and jump into initiating a payment. No product screenshots, docs, or community reports confirm such a consolidated search experience.", "evidenceIds": [ "brex-docs-12", "brex-docs-13", "brex-docs-11", "brex-docs-4" ] }, { "productId": "mercury", "storyId": "24-7-support-access", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of live customer support, phone/chat support hours, or urgent account-issue escalation channels; all evidence covers API/product/banking features and MCP/CLI tooling. Missing for 10: any documentation or claim about support channels, live/24-7 availability, or response times for urgent issues.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "accounting-software-sync", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury explicitly advertises syncing with QuickBooks, Xero, and NetSuite plus AI-powered receipt/category automation (mercury-docs-6, mercury-docs-5, mercury-docs-28), and its API exposes transaction/category/statement endpoints that could underlie such syncs (mercury-docs-12). However, this is purely first-party marketing copy with no docs detailing sync mechanics, frequency, or field-mapping, and no independent/hands-on confirmation that the QuickBooks/Xero/NetSuite sync works reliably in practice. Missing for 10: technical documentation of the sync mechanism, independent or community verification of accounting-software sync reliability, and detail on which transaction/expense fields are mapped.", "evidenceIds": [ "mercury-docs-6", "mercury-docs-5", "mercury-docs-28", "mercury-docs-12" ] }, { "productId": "mercury", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury explicitly documents an llms.txt endpoint for AI agents ('For AI agents: visit https://docs.mercury.com/llms.txt for an index of all pages formatted in Markdown and endpoints in OpenAPI. Append .md to any documentation page URL...'), and a live probe confirms llms.txt returns HTTP 200 with the expected markdown index content. This directly satisfies the story of pointing an agent at agent-oriented docs. Missing for 10: the OpenAPI spec referenced by llms.txt is not actually publicly downloadable (404s on all conventional paths, openapiVisibility set to admin-only), a minor inconsistency between the llms.txt promise and reality.", "evidenceIds": [ "mercury-docs-14", "mercury-probe-1", "mercury-probe-2", "mercury-probe-6" ] }, { "productId": "mercury", "storyId": "agentic-ai-insights", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Mercury offers AI-driven automation for specific workflows (auto-reading bills, auto-attaching receipts, AI-powered bookkeeping close) and an MCP server plus agent skills like mercury-analyze-spend and mercury-detect-anomaly that let AI query balances/transactions in natural language and surface anomalies. However, there's no evidence of proactive, in-product generated insights/dashboards (e.g., spend trend analysis, cash-flow forecasting, or automatic suggestions surfaced in the UI) — the MCP tools are read-only query/retrieval, not generative insight/suggestion features, and the skills repo is a separate CLI-driven agent toolkit rather than an in-product experience. missing for 10: proactive/native in-app AI insights or suggestions dashboard, evidence of forecasting or recommendation generation, independent confirmation these AI features produce actionable suggestions beyond data retrieval.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-6", "mercury-docs-5", "mercury-probe-5", "mercury-supp-agent-skills", "mercury-docs-32" ] }, { "productId": "mercury", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Mercury ships several automation primitives that can run in the background — webhooks/events API for reactive automation, auto-invoicing, AI-driven receipt matching and bookkeeping sync, plus an official CLI/API usable from scripts or CI pipelines and an 'agent skills' repo for CLI-driven automations. However, the flagship agent-facing surface (the hosted MCP server) is explicitly read-only (31 get/list tools, no write actions), so autonomous write-side actions (payments, invoices) would have to go through the API/CLI/webhooks rather than a persistent scheduled agent runtime, and no dedicated scheduler/cron/'run this automation on a trigger' product feature is documented. Missing for 10: a first-party scheduling/trigger engine for autonomous multi-step workflows, evidence of write-capable autonomous agent execution, and independent confirmation that background automations run reliably unattended.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-4", "mercury-docs-6", "mercury-docs-17", "mercury-docs-29", "mercury-probe-5", "mercury-supp-agent-skills", "mercury-probe-4" ] }, { "productId": "mercury", "storyId": "agentic-builtin-assistant", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Mercury exposes narrow AI-powered automations (bill scanning, receipt auto-attach, bookkeeping sync) and offers external interfaces (API, CLI, MCP server) for other agents/tools to connect to Mercury data, but there is no evidence of a built-in conversational AI assistant inside the Mercury product itself that a user can delegate tasks to.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-6", "mercury-probe-4", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "agentic-headless", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury ships an official CLI (mercury-cli, verified via probe: install, version, full command tree) explicitly runnable from terminal, script, or CI pipeline, plus a REST API with scoped API tokens, an OAuth2 flow, a sandbox environment, and an official Go SDK — all suitable for headless/CI automation. Docs explicitly state 'Run Mercury operations from your terminal, a script, or a CI pipeline' and provide sandbox base URLs for safe automated testing. missing for 10: no independent third-party report of the CLI actually running inside a CI pipeline end-to-end, no official npm/PyPI SDK (only Go), and no public OpenAPI spec download for tooling generation.", "evidenceIds": [ "mercury-docs-17", "mercury-docs-20", "mercury-probe-3", "mercury-docs-34", "mercury-supp-sandbox-base-urls", "mercury-supp-go-sdk", "mercury-docs-30" ] }, { "productId": "mercury", "storyId": "agentic-mcp-client", "verdict": "na", "quality": 0, "confidence": "medium", "rationale": "Mercury is a banking/fintech platform, not an AI agent or assistant host; its AI-native positioning is as an MCP *server* (mcp.mercury.com) that other agents connect to, not as a client/host that plugs in third-party MCP servers to gain their tools. There is no evidence of any Mercury interface (chat, agent, orchestrator) into which external MCP servers can be registered — the natural and only role evidenced is the reverse direction, so this client-side axis is a category error for this product.", "evidenceIds": [ "mercury-docs-22", "mercury-probe-4", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury ships an official, hosted MCP server at https://mcp.mercury.com/mcp, documented and independently verified live via probes showing OAuth2-gated (PKCE, dynamic client registration) access and a concrete inventory of 31 read-only tools (balances, transactions, cards, invoices, etc.), matching the docs' description of connecting agents to financial context. Missing for 10: write/action capabilities via MCP (currently read-only by design) and independent community corroboration of real-world agent usage beyond vendor docs/probes.", "evidenceIds": [ "mercury-docs-22", "mercury-docs-23", "mercury-docs-24", "mercury-docs-25", "mercury-probe-4", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 7, "confidence": "high", "rationale": "Mercury ships a live, OAuth-gated hosted MCP server confirmed via probe to support natural-language queries like 'What's my balance today?' and 'Graph my last 6 months of transactions' (mercury-docs-23, mercury-docs-32, mercury-probe-4). However, independent tool-inventory verification shows all 31 MCP tools are read-only (get*/list*) with zero write/send/create actions, so natural-language commands can query data but cannot execute operations like payments or invoice creation. missing for 10: natural-language-driven write/action capability (payments, transfers, invoice creation) via MCP, and broader hands-on confirmation beyond query examples.", "evidenceIds": [ "mercury-docs-23", "mercury-docs-32", "mercury-docs-18", "mercury-docs-31", "mercury-probe-4", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "agentic-official-cli", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Mercury ships an official, actively maintained CLI (mercury-cli, Mercury's own GitHub org) with a documented installer, verified working `--version`/`--help`, full resource command tree (accounts, cards, payments, invoices, treasury, etc.), auth flows, sandbox/production environments, and even an official agent-skills repo built specifically to drive the CLI for AI-native workflows. missing for 10: independent third-party (non-Mercury) reviews or adoption reports of the CLI specifically, and confirmation of write-action success beyond documented help output.", "evidenceIds": [ "mercury-probe-3", "mercury-supp-agent-skills", "mercury-docs-17" ] }, { "productId": "mercury", "storyId": "agentic-public-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Mercury publishes a comprehensive, versioned REST API (accounts, cards, transactions, invoices, payments, treasury) with interactive docs, OAuth2 and scoped API tokens, a sandbox environment, an official Go SDK, and an official CLI (verified via probe) covering the full resource surface — clearly documented and independently confirmed as working. It also explicitly caters to AI agents via llms.txt, agent skills repo, and a hosted MCP server. missing for 10: no publicly downloadable OpenAPI spec (confirmed gated to admin-only) and no official Python/Node SDKs, only community packages.", "evidenceIds": [ "mercury-docs-12", "mercury-docs-13", "mercury-docs-14", "mercury-docs-15", "mercury-docs-20", "mercury-probe-3", "mercury-supp-sandbox-base-urls", "mercury-supp-interactive-docs", "mercury-supp-go-sdk", "mercury-probe-6" ] }, { "productId": "mercury", "storyId": "agentic-scoped-keys", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury documents scoped/least-privilege credential issuance for agents: read-only, read-write, and custom API tokens (mercury-docs-35), 'Issue scoped API tokens with fine-grained permissions' (mercury-docs-20), OAuth2 authorization flows (mercury-docs-15), and dashboard-based revocation (mercury-docs-25). This is independently corroborated by a live probe of the hosted MCP server showing OAuth2/PKCE-gated access with explicit granular scopes (read, offline_access) and a read-only-only tool inventory (mercury-probe-4, mercury-probe-5), confirming scoped agent credentials work in practice. Missing for 10: independent hands-on verification of actually minting a 'custom' scoped token end-to-end and assigning it to a live agent workflow.", "evidenceIds": [ "mercury-docs-20", "mercury-docs-35", "mercury-docs-25", "mercury-docs-15", "mercury-probe-4", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "agentic-sdks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Mercury ships one official SDK (Go, generated via Stainless) plus a public REST API, official CLI, and MCP server, giving AI-native builders real programmatic surface area, but there is no official JS/TypeScript or Python SDK — only community packages (e.g. n8n-nodes-mercury) — and the OpenAPI spec is deliberately kept non-public (openapiVisibility:'admin'), limiting SDK-generation/tooling for other languages. missing for 10: official SDKs in mainstream AI-stack languages (JS/Python), publicly downloadable OpenAPI spec, independent hands-on confirmation of SDK usage beyond docs.", "evidenceIds": [ "mercury-supp-go-sdk", "mercury-supp-agent-skills", "mercury-probe-3", "mercury-probe-6", "mercury-docs-16", "mercury-docs-30" ] }, { "productId": "mercury", "storyId": "agentic-webhooks", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Mercury's Accounts Receivable API explicitly documents webhook endpoint management (Create/Update/Verify/Get/Delete) and an Events API to retrieve emitted events, and the CLI also exposes a dedicated 'webhooks' resource command, confirming first-class webhook subscription support. Missing for 10: independent/hands-on confirmation of actually receiving a webhook payload, and documentation of supported event types/payload schemas.", "evidenceIds": [ "mercury-docs-13", "mercury-probe-3" ] }, { "productId": "mercury", "storyId": "ai-anomaly-spend-detection", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "The official mercury-skills repo lists a 'mercury-detect-anomaly' skill for the Mercury CLI, indicating an AI-driven anomaly-detection capability exists, but there is no documentation of how it works, whether it flags out-of-policy transactions specifically, or how review/approval is triggered. Missing for 10: detailed docs on anomaly/policy-violation detection logic, automatic flagging-for-review workflow, and independent confirmation the skill functions as described.", "evidenceIds": [ "mercury-supp-agent-skills" ] }, { "productId": "mercury", "storyId": "ai-bill-data-extraction", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury explicitly markets an AI bill-pay feature that reads bills, auto-populates payment details, and remembers past recipients for quick approval, directly matching the story (mercury-docs-3). However, this is a single marketing-line claim with no deeper documentation of the review/approval workflow, no independent or hands-on corroboration, and the separate MCP tool inventory confirms only read-only capabilities with no bill-reading or auto-populate tools exposed there. Missing for 10: detailed product documentation of the bill-reading/approval UI, independent user reports confirming accuracy, and API/MCP support for this specific workflow.", "evidenceIds": [ "mercury-docs-3", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "ai-books-close-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Mercury explicitly advertises syncing with QuickBooks, Xero, and NetSuite plus AI-powered automations to 'close your books faster' (mercury-docs-6), backed by supporting AI automation features like auto-reading bills, auto-attaching receipts, and API write actions for categorizing transactions/invoices (mercury-docs-3, mercury-docs-5, mercury-docs-29). Missing for 10: independent/hands-on verification that the accounting sync and AI automations actually reduce close time, and no detail on depth of QBO/Xero/NetSuite reconciliation accuracy.", "evidenceIds": [ "mercury-docs-6", "mercury-docs-3", "mercury-docs-5", "mercury-docs-29", "mercury-docs-19" ] }, { "productId": "mercury", "storyId": "ai-contract-parsing-procurement", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Mercury's AI document-reading is limited to bills for bill-pay (auto-populating bill details) and receipt auto-attach; there is no evidence of parsing vendor contracts or auto-populating procurement request forms, which is a distinct workflow not covered in any docs, API, or MCP tool inventory.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-5", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "ai-gl-coding-automation", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Mercury's docs mention 'AI-powered automations to close your books faster' when syncing with QuickBooks/Xero/NetSuite, and the API exposes a Categories resource plus 'Update transaction metadata' endpoint, suggesting some categorization/GL-code capability. However, there is no concrete evidence of AI automatically assigning GL codes specifically, nor any support for multi-entity operations. Missing for 10: explicit documentation of automated GL-code/category assignment logic, evidence of multi-entity/consolidated close workflows, and any hands-on or independent confirmation of this working in practice.", "evidenceIds": [ "mercury-docs-6", "mercury-docs-12" ] }, { "productId": "mercury", "storyId": "ai-price-monitoring-rebooking", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a business banking/finance platform (cards, payments, invoicing, treasury); travel booking and travel-rate monitoring/rebooking is entirely outside its product category, not a banking feature.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "api-interactive-docs", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury's docs.mercury.com/reference hub is a ReadMe-based interactive API reference with a live 'Try It!' request runner, language-specific code samples (Shell, Node, Ruby, PHP, Python), Bearer auth field, and real endpoint schemas, backed by a sandbox environment for safe testing. This is corroborated by probes confirming the reference page loads and the sandbox base URLs work. Missing for 10: publicly downloadable OpenAPI spec (confirmed 404/admin-only via probes), and no independent hands-on account of actually running examples through the 'Try It' button.", "evidenceIds": [ "mercury-supp-interactive-docs", "mercury-supp-sandbox-base-urls", "mercury-probe-6", "mercury-docs-34" ] }, { "productId": "mercury", "storyId": "api-machine-spec", "verdict": "disputed", "quality": 4, "confidence": "high", "rationale": "Mercury's llms.txt claims endpoints are documented 'in OpenAPI' format for AI agents (mercury-docs-14), and the docs hub has an interactive API reference, but direct probes of all standard OpenAPI spec paths return 404, and the reverify probe confirms the OpenAPI 3.0 definitions exist internally but are deliberately hidden from public download (showOpenAPIDownload:false, openapiVisibility:admin). So the claimed machine-readable spec is not actually obtainable by an AI-native user. Missing for 10: a publicly downloadable OpenAPI/JSON spec file, confirmation the llms.txt claim resolves to an actual retrievable machine-readable spec.", "evidenceIds": [ "mercury-docs-14", "mercury-probe-2", "mercury-probe-6" ] }, { "productId": "mercury", "storyId": "api-sandbox", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Mercury documents a dedicated sandbox environment (sandbox.mercury.com/signup, api-sandbox.mercury.com base URL, oauth2-sandbox base URL) explicitly stated to use 'dummy data' with 'no real money involved,' and production tokens are rejected in sandbox, enforcing isolation; the API docs and CLI also expose an --environment sandbox|production flag confirming first-class sandbox support across API and CLI. missing for 10: no independent/hands-on community report of actually using the sandbox (only vendor docs and a CLI probe showing the flag exists, not an end-to-end sandbox test transcript).", "evidenceIds": [ "mercury-docs-30", "mercury-docs-34", "mercury-supp-sandbox-base-urls", "mercury-probe-3" ] }, { "productId": "mercury", "storyId": "api-versioning-policy", "verdict": "partial", "quality": 6, "confidence": "high", "rationale": "Mercury's API is clearly versioned (/api/v1/, with a v1-pre/v1/v2 version picker) and Mercury publishes a dated public changelog with migration guidance for breaking changes (e.g. the credit statement sign-convention change), showing real practice around versioning and change management. However, the evidence explicitly states no written deprecation/sunset policy page exists anywhere on docs.mercury.com, so there is no formal documented policy an AI-native integrator could point to for guarantees on deprecation timelines. missing for 10: a published formal deprecation/sunset policy document, explicit version-lifecycle/support-window commitments, and independent confirmation that breaking changes are always preceded by adequate notice.", "evidenceIds": [ "mercury-supp-versioned-api-docs", "mercury-supp-changelog-migration", "mercury-supp-interactive-docs" ] }, { "productId": "mercury", "storyId": "application-status-tracking", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Mercury's onboarding application flow (apply online, CLI 'Onboarding (apply)' command) but nothing about being able to check or track the status of an application while it's under review — no dashboard, CLI, or API endpoint for application/review status is documented anywhere in the pack.", "evidenceIds": [ "mercury-docs-26", "mercury-probe-3" ] }, { "productId": "mercury", "storyId": "auto-cash-topup-alerts", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "A long-time customer describes creating 'dozens of purpose-named accounts with auto-funding rules' (mercury-comm-1), which is real-world evidence of auto top-up/fund-transfer automation between accounts, and Mercury's Treasury product (mercury-docs-39) supports the treasury-yield angle. However, there is no vendor documentation describing configurable auto top-up rules or low-balance alert features anywhere in the docs/API/MCP evidence. missing for 10: first-party docs on auto top-up configuration, explicit low-balance alert/notification feature, and any API/webhook evidence for balance threshold alerts.", "evidenceIds": [ "mercury-comm-1", "mercury-docs-39" ] }, { "productId": "mercury", "storyId": "auto-receipt-capture-on-swipe", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury lets users email or upload receipts and auto-attaches them to the matching card transaction (mercury-docs-5/28), and there's a mercury-receipt-upload agent skill for automating this (mercury-supp-agent-skills), plus a transaction-attachment API endpoint (mercury-docs-12). However, this is not truly automatic capture 'the moment a card is used' — it requires the user to email/upload the receipt themselves rather than passive/automatic capture at time of swipe, and there's no OCR/auto-coding of receipt line items into categories mentioned, only attachment matching. Missing for 10: evidence of automatic receipt capture without any manual send/upload step (e.g., via merchant integration or physical receipt scanning at point of sale), evidence of automatic line-item categorization/coding from receipt contents, and independent/hands-on confirmation this works reliably in practice.", "evidenceIds": [ "mercury-docs-5", "mercury-docs-28", "mercury-supp-agent-skills", "mercury-docs-12" ] }, { "productId": "mercury", "storyId": "automatic-invoice-followup", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Mercury offers invoicing features (manual/automatic invoice creation, Accounts Receivable API for invoices, customers, webhooks/events) but no evidence describes automated reminders or follow-up chasing on overdue/unpaid invoices specifically. The invoicing API supports create/list/get/update/cancel operations, not a documented dunning or overdue-reminder workflow.", "evidenceIds": [ "mercury-docs-4", "mercury-docs-13", "mercury-docs-19", "mercury-docs-21" ] }, { "productId": "mercury", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury exposes per-resource CRUD endpoints (cards, invoices, transactions, categories) and a CLI/API that let scripts loop to create many cards or invoices, and a real customer reports creating 'hundreds of virtual debit cards' and 'dozens of purpose-named accounts' this way. However there's no documented native bulk/batch endpoint (e.g. batch-create invoices/cards in one call), and the MCP server is entirely read-only (list/get only, no write tools), so bulk write actions must be hand-scripted item-by-item via the REST API or CLI rather than a first-class bulk operation feature. Missing for 10: a documented batch/bulk-create API endpoint, bulk operations support in the MCP/agent surface, and vendor documentation explicitly describing bulk workflows.", "evidenceIds": [ "mercury-docs-2", "mercury-docs-21", "mercury-comm-1", "mercury-probe-3", "mercury-probe-5", "mercury-docs-13" ] }, { "productId": "mercury", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Mercury exposes an Events/Webhooks API (create/update/verify webhook endpoints, get events) that lets external systems react to account events, and ships some built-in automatic behaviors (auto-attach receipts, automatic cashback deposit, AI bill-reading automations). However there is no evidence of a native in-product 'if event X then action Y' rule-builder that AI-native users can configure themselves — webhooks require the user to build their own listener/automation logic outside Mercury, and MCP tools are read-only so agents cannot trigger write actions from natural-language rules. Missing for 10: a documented rules/automation engine or trigger-action builder inside Mercury, and evidence that MCP/agent tooling can autonomously execute rule-based actions.", "evidenceIds": [ "mercury-docs-13", "mercury-docs-6", "mercury-docs-5", "mercury-docs-8", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Mercury offers some recurring, automation-like features (automatic invoices, AI-powered bill-pay automations, auto-funding rules for accounts) but there is no evidence of a general-purpose scheduler or 'recurring job/workflow' API, CLI command, or MCP tool that an AI-native user could invoke to schedule arbitrary tasks. The MCP server is explicitly read-only (31 get/list tools) and the CLI/API expose transactional resources, not job scheduling. Missing for 10: dedicated recurring-job/cron API or MCP tool, evidence of scheduling arbitrary workflows beyond built-in invoice/bill automations, and any documentation of a scheduler for AI agents.", "evidenceIds": [ "mercury-docs-4", "mercury-docs-6", "mercury-docs-3", "mercury-comm-1", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Mercury's API, CLI, MCP server, and sandbox for building integrations/automations, plus an API changelog for endpoint version history, but nothing about versioning, reviewing, or rolling back user-created automations themselves (e.g., no workflow/rule history, diff, or undo mechanism for automations built on top of Mercury).", "evidenceIds": [] }, { "productId": "mercury", "storyId": "bank-verification-letter", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers cards, payments, invoicing, API/MCP tooling, and statement PDF downloads, but nowhere mentions displaying account/routing numbers or generating a bank verification letter — a standard banking feature that a business bank like Mercury could plausibly offer, but no evidence confirms it exists.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "bill-pay-approval-workflow", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Mercury's bill-pay feature explicitly supports uploading/reading bills via AI and an approve-then-pay flow (mercury-docs-3), plus granular permissions letting specific roles (e.g., an accountant) execute payments (mercury-docs-11) and spend/approval controls (mercury-docs-10, mercury-docs-38). The MCP tool inventory also lists dedicated approval-workflow endpoints like listSendMoneyApprovalRequests and getSafeRequest(s) (mercury-probe-5), corroborating a real multi-step approval mechanism for vendor payments. Missing for 10: no first-party documentation detailing the full workflow UI/steps (multi-approver routing rules, thresholds), and no independent/hands-on user report specifically validating the bill-approval process end-to-end.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-11", "mercury-docs-10", "mercury-docs-38", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "budget-based-spend-enforcement", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury supports per-card spending limits, spend controls, and granular user permissions (mercury-docs-10, mercury-docs-38), and the Cards API lets you 'manage spending limits' programmatically (mercury-docs-36), which enforces spend caps at the card/user level. However, there is no evidence of a dedicated department- or program-level 'budget' object that aggregates multiple cards/users under one enforced ceiling — only individual card limits and role-based permissions are documented. Missing for 10: explicit department/program budget creation, budget rollup/aggregation across multiple cards or cost centers, and automatic alerts/enforcement tied to a program-level allocation rather than per-card limits.", "evidenceIds": [ "mercury-docs-10", "mercury-docs-36", "mercury-docs-38", "mercury-docs-11" ] }, { "productId": "mercury", "storyId": "card-spend-limits-controls", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury explicitly markets per-card spend limits and granular permissions ('Curb team spend with card limits, spend controls, and granular user permissions'), backed by virtual card creation, card lifecycle/limit management via API, and independent community confirmation of creating hundreds of virtual cards with individual limits. missing for 10: no hands-on walkthrough of setting a specific per-employee limit in the UI, and no detail on the granularity of permission types available to finance leads beyond marketing copy.", "evidenceIds": [ "mercury-docs-10", "mercury-docs-2", "mercury-docs-36", "mercury-docs-38", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "consolidate-point-solutions", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury documents a unified platform covering banking, virtual/physical cards with spend controls, bill pay with AI-assisted invoice reading, AR/invoicing, receipt auto-attachment, accounting sync (QuickBooks/Xero/NetSuite), Treasury yield, and FX/international payments, all inside one account — directly consolidating spend, bill pay, and banking tools. Independent community evidence (5-year customer) corroborates real-world use across cards, wires, and multi-account structures replacing other tools. missing for 10: no independent evidence of replacing named specific competitor point-solutions (e.g., Expensify/Bill.com) or third-party case studies quantifying tool consolidation.", "evidenceIds": [ "mercury-docs-2", "mercury-docs-3", "mercury-docs-4", "mercury-docs-5", "mercury-docs-6", "mercury-docs-7", "mercury-docs-10", "mercury-docs-38", "mercury-docs-39", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "dedicated-accounting-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Mercury publishes a dedicated REST API with extensive accounting-related resources — transactions, categories, statements, invoices, customers/AR, webhooks, treasury — supporting both viewing (list/get) and managing (create/update/delete/cancel) data, backed by OAuth2, scoped tokens, a sandbox environment, versioned docs, an official CLI (verified working via probe), and a Go SDK. Probes independently confirm the CLI installs and lists real resource commands and the sandbox/interactive docs are functional, giving strong first-party plus hands-on corroboration.\nMissing for 10: independent third-party developer reviews of the core REST API itself (vs. MCP) and a publicly downloadable OpenAPI spec (confirmed internal-only via probe).", "evidenceIds": [ "mercury-docs-12", "mercury-docs-13", "mercury-docs-15", "mercury-docs-34", "mercury-docs-35", "mercury-probe-3", "mercury-supp-sandbox-base-urls", "mercury-supp-interactive-docs", "mercury-supp-versioned-api-docs", "mercury-supp-go-sdk", "mercury-probe-6" ] }, { "productId": "mercury", "storyId": "earn-yield-on-balances", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Mercury explicitly offers 'Treasury by Mercury Advisory' with yield up to 3.89% directly within the Mercury account/dashboard, alongside free checking/savings, so operating cash can earn yield without moving funds to a separate institution. Missing for 10: independent/hands-on verification of the yield product's mechanics (e.g., sweep structure, FDIC coverage details) and community corroboration of actual yield experience beyond the vendor claim.", "evidenceIds": [ "mercury-docs-39" ] }, { "productId": "mercury", "storyId": "embedded-banking-no-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Mercury's evidence describes a business bank account plus an API/MCP/CLI for managing that single business's own accounts, cards, invoices, and payments — not a banking-as-a-service platform for issuing white-labeled accounts to a developer's end customers under Mercury's charter. Nothing in the docs, changelog, SDKs, or API catalog mentions account issuance for third-party end users, program management, or BaaS partnership terms.", "evidenceIds": [ "mercury-docs-16", "mercury-docs-13", "mercury-docs-29", "mercury-probe-3", "mercury-probe-5" ] }, { "productId": "mercury", "storyId": "fast-cross-border-transfer", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Mercury advertises 'no-fee USD payments around the globe' but nothing in the evidence specifies transfer speed, let alone a sub-minute arrival time for international payments; typical wire/ACH rails imply multi-day settlement, and no probe or doc confirms near-instant delivery abroad.", "evidenceIds": [ "mercury-docs-7" ] }, { "productId": "mercury", "storyId": "fast-onboarding-switch", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury explicitly advertises rapid onboarding (\"Apply online in 10 minutes\") and near-instant account usability (\"business credit cards as soon as day one — no minimums, credit checks, or personal guarantees\"), directly supporting a week-vs-months onboarding claim. However, this is vendor marketing copy only — no independent/community account of an actual end-to-end onboarding timeline, KYC/compliance steps, or founder testimonials confirming real-world speed. Missing for 10: independent or hands-on confirmation of onboarding duration, detail on KYC/compliance steps, and founder testimonials specifically about onboarding speed.", "evidenceIds": [ "mercury-docs-26", "mercury-docs-27" ] }, { "productId": "mercury", "storyId": "fdic-insurance-sweep", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Mercury markets Treasury sweep accounts (mercury-docs-39 mentions 'Treasury by Mercury Advisory' yield) but no evidence describes automatic sweeping of deposits across multiple partner banks specifically to maximize FDIC coverage — the docs focus on cards, invoicing, API/MCP tooling, and yield, not multi-bank FDIC sweep networks.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "fee-free-foreign-card-spend", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers card issuance, virtual cards, cashback, and no-fee USD payments/transfers, but nothing addresses foreign transaction fees, currency conversion fees, or ATM cash withdrawal abroad on a Mercury card. 'No-fee USD payments around the globe' (mercury-docs-7) refers to outbound payments, not card spend/withdrawal abroad, so it does not substantiate this specific claim.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "freeze-replace-card", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Mercury lets you retrieve cards and, via the Cards API, 'manage spending limits and control card lifecycle states' (mercury-docs-1, mercury-docs-36), which plausibly covers freezing/deactivating a card, but there is no explicit documentation of a 'freeze card' action or of ordering a physical replacement card for a lost/stolen card. missing for 10: explicit freeze/lock card documentation, explicit lost/stolen card replacement flow, UI or API evidence of the finance-lead-facing freeze button.", "evidenceIds": [ "mercury-docs-1", "mercury-docs-36", "mercury-docs-2" ] }, { "productId": "mercury", "storyId": "gl-sync-erp", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Mercury advertises syncing with QuickBooks, Xero, and NetSuite to help close books faster (mercury-docs-6), which addresses the ERP-integration theme, but there is no detail confirming true real-time bidirectional sync (versus periodic export/import) or automated journal-entry creation, and no independent/hands-on evidence validating the sync's reliability or completeness. Missing for 10: documentation of bidirectional data flow direction, real-time sync frequency/latency, automated journal entry mapping, and independent confirmation the integration works as described.", "evidenceIds": [ "mercury-docs-6" ] }, { "productId": "mercury", "storyId": "high-yield-savings-subaccount", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury offers a high-yield Treasury product (up to 3.89% yield) and supports multiple purpose-named sub-accounts, and a long-tenure customer reports using 'auto-funding rules' across dozens of these accounts, supporting the described workflow. However, there is no official documentation describing a dedicated 'automated transfer rule' feature or explicit high-yield savings sub-account mechanics — this evidence comes only from a single community anecdote, not vendor docs or API endpoints. Missing for 10: official docs on automated/recurring transfer rule configuration, explicit sub-account-to-Treasury auto-sweep feature documentation, and independent verification beyond one HN comment.", "evidenceIds": [ "mercury-docs-39", "mercury-docs-12", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "instant-virtual-card-issuance", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury's docs explicitly market instant virtual card creation scoped to purposes like ad spend or vendor use, backed by spend controls/limits and an API for issuing/managing card lifecycle, and a 5-year customer corroborates creating hundreds of individually-limited virtual cards in practice. Missing for 10: explicit documentation of merchant-lock/single-vendor restriction mechanics beyond naming and limits, and independent confirmation specifically of 'purpose-scoped' (vs just limited) cards.", "evidenceIds": [ "mercury-docs-2", "mercury-docs-10", "mercury-docs-36", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "invoice-creation-collection", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Mercury explicitly supports sending manual/automatic invoices with flexible payment methods and customer management (mercury-docs-4), a dedicated Invoices API (create/list/get/update/cancel, download PDF) (mercury-docs-13), and invoice volume tied to paid plans (mercury-docs-21). However, evidence does not confirm invoice 'branding' customization (logos/colors) or hands-on/community confirmation of the invoicing UX itself. missing for 10: independent/hands-on evidence of invoice branding customization options, and third-party confirmation of the payment-collection experience from a customer's perspective.", "evidenceIds": [ "mercury-docs-4", "mercury-docs-13", "mercury-docs-21", "mercury-docs-19" ] }, { "productId": "mercury", "storyId": "lock-exchange-rate", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a US-focused business banking/payments product primarily dealing in USD (no-fee USD payments); there is no evidence of FX/multi-currency transfer features at all, let alone a rate-lock mechanism. Locking an exchange rate for a fixed window is a cross-border FX product feature that doesn't fit Mercury's documented scope of domestic USD banking, cards, invoicing, and API/MCP tooling.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "multi-currency-account-creation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Mercury offers USD checking/savings/Treasury accounts and no-fee USD international payments (mercury-docs-7, mercury-docs-39), but nothing indicates the ability to hold or manage balances in foreign currencies (e.g., EUR, GBP) within a single account — all documented balances, cards, and API/MCP tools reference USD only. Missing for 10: any documentation of multi-currency account creation, foreign-currency balance holding, or currency conversion/FX management features.", "evidenceIds": [ "mercury-docs-7", "mercury-docs-39", "mercury-docs-24" ] }, { "productId": "mercury", "storyId": "multi-currency-interest", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Mercury offers yield via 'Treasury by Mercury Advisory' (up to 3.89%) but this and all cash/banking references are USD-only — there is no mention of interest-bearing balances in multiple currencies, multi-currency accounts, or FX-denominated yield anywhere in the pack. Missing for 10: any documentation of multi-currency account holding, multi-currency interest rates, or FX yield products.", "evidenceIds": [ "mercury-docs-39", "mercury-docs-7" ] }, { "productId": "mercury", "storyId": "multiple-checking-subaccounts", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "A long-term hands-on user reports creating 'dozens of purpose-named accounts with auto-funding rules,' directly confirming both multiple checking sub-accounts and automated allocation of funds across them. No first-party Mercury docs in the pack explicitly describe the sub-account/auto-allocation feature or its configuration options, so evidence rests on a single community account rather than documented capability. Missing for 10: first-party docs on creating sub-accounts and configuring auto-allocation rules, and additional independent corroboration.", "evidenceIds": [ "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "no-fee-card-cashback", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Mercury explicitly advertises automatic, unlimited cashback deposited directly into the account with no manual redemption or points system, and separately states a concrete 1.5% cashback rate on credit card spend, directly matching the founder story. Missing for 10: independent/community corroboration that the cashback mechanic works as described in practice, and clarity on whether it applies uniformly to debit vs credit cards.", "evidenceIds": [ "mercury-docs-8", "mercury-docs-38" ] }, { "productId": "mercury", "storyId": "one-click-payment-approval", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Mercury docs explicitly describe granular user permissions and built-in approval permissions that let designated teammates (e.g. an accountant) approve and send payments in one click, and product marketing highlights team spend controls with approvals. Community evidence corroborates real-world use of card/account permission controls, though not specifically the one-click approval flow. Missing for 10: independent/hands-on confirmation of the one-click approval UX itself and detail on how granular approval roles are configured (e.g., approval thresholds, multi-approver workflows).", "evidenceIds": [ "mercury-docs-10", "mercury-docs-11", "mercury-docs-38", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "openness-api-parity", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Mercury's REST API, CLI, and SDK expose most core UI actions—accounts, transactions, card issuance/lifecycle, invoices/customers, categories, statements, webhooks, ACH payments, and even Vault agent-card credentials (mercury-docs-12,13,36,37; mercury-probe-3)—with sandbox, versioning, and changelog support. However parity is incomplete: the AI bill-reading/bill-pay flow (mercury-docs-3) has no documented API equivalent, and the hosted MCP surface is explicitly read-only (31 get/list tools, zero write actions per mercury-probe-5), meaning an AI agent using MCP cannot perform actions like payments or invoice creation that a human can in the UI. Missing for 10: documented API/CLI parity for bill-pay AI feature, write-capable MCP tools matching UI actions, and confirmation that all UI-only conveniences (universal search, cashback redemption) have functional API analogs.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-12", "mercury-docs-13", "mercury-docs-29", "mercury-docs-36", "mercury-docs-37", "mercury-probe-3", "mercury-probe-5", "mercury-probe-4" ] }, { "productId": "mercury", "storyId": "openness-full-export", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Mercury exposes transactions, statements (PDF), categories, invoices, and account data via a documented REST API and CLI, which provides a path to programmatically export financial data in standard formats (JSON, PDF). However, there is no evidence of a dedicated 'export all my data' bulk-export feature, no mention of CSV/standard banking export formats beyond PDF statements, and no documentation addressing account closure or leaving with full data portability guarantees. missing for 10: a documented full-account data export/closure workflow, explicit open standard formats (e.g., CSV/OFX) beyond PDF, and any guarantee of data portability upon account closure.", "evidenceIds": [ "mercury-docs-12", "mercury-docs-16", "mercury-probe-3", "mercury-supp-sandbox-base-urls" ] }, { "productId": "mercury", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a proprietary banking/fintech product, not open-source software; the question of reading its source under an open license is a category error for this type of product (a bank platform), not an applicable openness axis.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a hosted banking/fintech SaaS platform (accounts, cards, payments, API/MCP access to a regulated financial service); self-hosting the 'core product' is a category error since banking infrastructure cannot be run by customers themselves — this axis does not apply to this kind of product.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "physical-card-issuance", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Mercury documents issuing business debit/credit cards to employees with spend limits and granular permissions (mercury-docs-10, mercury-docs-27, mercury-docs-38, mercury-docs-1), and a community user confirms creating many cards with individual limits (mercury-comm-1). However most product copy emphasizes virtual cards (mercury-docs-2) and no evidence explicitly details a physical-card issuance workflow tied to defined employee roles. Missing for 10: explicit documentation of physical card ordering/shipping process, and role-based (not just limit-based) card issuance controls.", "evidenceIds": [ "mercury-docs-10", "mercury-docs-27", "mercury-docs-38", "mercury-docs-1", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "po-matched-invoice-automation", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Mercury's bill pay AI reads and auto-populates bill details and remembers recipients for quick approval (mercury-docs-3), and permissions allow routing payments to approvers like accountants (mercury-docs-11), but there is no evidence of purchase-order matching or GL/expense coding logic tying invoices to POs — core parts of the described workflow are unevidenced. missing for 10: purchase order matching/reconciliation, explicit invoice coding to GL categories tied to POs, and a documented multi-step approval routing workflow for AP.", "evidenceIds": [ "mercury-docs-3", "mercury-docs-11", "mercury-docs-10" ] }, { "productId": "mercury", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence anywhere in the pack addresses data residency, regional storage options, or geographic control over where account/API/MCP data is stored; Mercury's docs, API, and MCP materials are silent on this axis despite it being a fair question for a financial data platform serving international customers. Missing for 10: any mention of data region selection, residency guarantees, or geo-specific storage/compliance options.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "privacy-no-training", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a business banking/API platform, not an AI model provider or consumer content service that trains models on user data — the 'prevent my data from being used to train AI models' privacy axis doesn't apply to this category of product.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows only the ability to revoke MCP/API access (mercury-docs-25), but nothing about controlling data retention periods or deleting stored/processed data for AI-native usage; banking retention requirements make this a fair question but no capability is documented.", "evidenceIds": [ "mercury-docs-25" ] }, { "productId": "mercury", "storyId": "privacy-telemetry-optout", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Mercury is a banking/fintech platform, not an AI tool that itself collects/transmits telemetry about a user's usage of the product—no evidence pack item addresses telemetry opt-out and this axis is a mismatch for a financial services product's evidence.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "receipt-matching-by-email-upload", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Mercury's docs explicitly state receipts can be emailed or uploaded and are auto-attached to the correct card transaction, directly matching the story, with API support for uploading transaction attachments. missing for 10: independent/hands-on confirmation (e.g. community report) that auto-attach matching works reliably in practice, and no detail on edge cases (mismatched/ambiguous receipts).", "evidenceIds": [ "mercury-docs-5", "mercury-docs-28", "mercury-docs-29", "mercury-docs-12" ] }, { "productId": "mercury", "storyId": "receive-multi-currency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Mercury offers USD checking/savings accounts and sending no-fee USD payments globally, but there is no evidence of local currency receiving account details (e.g., local IBAN/EUR, GBP, local clearing numbers) for accepting multi-currency payments — this is a fair question for a business banking product but Mercury's evidence pack is USD-centric throughout.", "evidenceIds": [ "mercury-docs-7", "mercury-docs-39" ] }, { "productId": "mercury", "storyId": "request-limit-increase", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Mercury documents self-service control over card spend limits (\"Curb team spend with card limits, spend controls\" and API support to \"manage spending limits\"), which lets an admin set/adjust limits directly rather than submit a request for approval. There is no explicit evidence of a dedicated 'request a transaction/credit limit increase' self-service screen or approval workflow. Missing for 10: explicit UI/flow for submitting and approving a limit-increase request, confirmation this applies to overall account/credit limits (not just per-card spend caps), and independent/hands-on verification of the flow.", "evidenceIds": [ "mercury-docs-10", "mercury-docs-36", "mercury-docs-38" ] }, { "productId": "mercury", "storyId": "role-based-permissions", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Mercury explicitly advertises 'granular user permissions' and 'built-in permissions' allowing role-differentiated access (e.g., accountant given payment-only access) plus scoped/read-only/read-write/custom API tokens, which supports role-based access control for a finance lead. However, there is no evidence of permission structuring specifically by location or department, or of a full admin UI showing role/permission matrix management. Missing for 10: documentation of location- or department-level permission scoping, a detailed permissions matrix/UI walkthrough, and independent confirmation of granular role management beyond marketing claims.", "evidenceIds": [ "mercury-docs-10", "mercury-docs-11", "mercury-docs-20", "mercury-docs-35" ] }, { "productId": "mercury", "storyId": "send-domestic-ach-wire", "verdict": "full", "quality": 7, "confidence": "high", "rationale": "Mercury's core banking product supports sending ACH transfers and wires, evidenced by API docs referencing 'initiate ACH transfers' and payment creation (mercury-docs-16, mercury-docs-29, mercury-docs-9), plus independent community corroboration of reliable wire transfers in production use (mercury-comm-1). AI bill-pay features (mercury-docs-3) further support vendor payment workflows for finance leads. missing for 10: dedicated documentation detailing wire vs ACH fees, transfer limits, cutoff times, and a full end-to-end vendor payment approval workflow beyond generic mentions.", "evidenceIds": [ "mercury-docs-16", "mercury-docs-29", "mercury-docs-9", "mercury-docs-3", "mercury-comm-1" ] }, { "productId": "mercury", "storyId": "send-international-payments", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Mercury's documented international payment feature is explicitly USD-only ('Send no-fee USD payments around the globe' — mercury-docs-7), with no evidence of multi-currency/local-currency payment support, FX conversion, or transparent FX fee disclosure anywhere in the API, MCP, or product docs.", "evidenceIds": [ "mercury-docs-7" ] }, { "productId": "mercury", "storyId": "transfer-delivery-estimate", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack covers cards, invoicing, API/MCP/CLI tooling, and sandbox testing, but nothing describes a transfer confirmation UI showing an estimated delivery date/time for ACH or wire payments before the user confirms.", "evidenceIds": [] }, { "productId": "mercury", "storyId": "universal-transaction-search", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Mercury's own marketing docs explicitly describe a universal search bar to find any transaction, vendor, or card and jump straight into creating payments/transfers, directly matching the story. missing for 10: no independent/hands-on verification or screenshots of the search UI in action, and no community corroboration of this specific feature.", "evidenceIds": [ "mercury-docs-9" ] }, { "productId": "ramp", "storyId": "24-7-support-access", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions live customer support, support channels, response times, or availability guarantees; the pack only covers product features, integrations, and general community sentiment unrelated to support access.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "accounting-software-sync", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Ramp documents real-time bidirectional ERP sync, automatic categorization/coding synced directly to accounting systems, and a broad list of accounting integrations (NetSuite, QuickBooks, Xero, Sage Intacct, etc.), plus community corroboration of the platform working well for expense tracking. missing for 10: independent hands-on verification specifically of accounting-sync accuracy/reconciliation rather than vendor claims.", "evidenceIds": [ "ramp-docs-5", "ramp-docs-15", "ramp-intdir-1", "ramp-docs-12", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Ramp publishes a documented llms.txt indexing structure (llms.txt, llms-guides.txt, llms-api.txt, llms-full.txt, OpenAPI spec) explicitly designed for LLM/agent consumption, and a live probe confirms HTTP 200 with machine-readable usage instructions. Missing for 10: independent third-party corroboration of an agent actually consuming these files in a real workflow.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-10", "ramp-docs-11", "ramp-probe-1" ] }, { "productId": "ramp", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp documents multiple AI-generated insights/suggestions embedded in the product itself: auto-filled memos/categories at swipe, AI-driven invoice coding and matching, hotel rebooking suggestions, contract/screenshot parsing for intake, and dedicated AI agents for coding, fraud, approvals and payments. These are first-party claims with some corroboration via community praise of smooth automated workflows (e.g., instant card issuance and approval flows), though independent verification of the 'AI-generated insight' quality specifically is thin. Missing for 10: independent hands-on evaluation of AI insight accuracy/usefulness, and clearer distinction between rule-based automation vs. true generative insights.", "evidenceIds": [ "ramp-docs-1", "ramp-docs-2", "ramp-docs-3", "ramp-docs-4", "ramp-docs-15", "ramp-docs-17", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "agentic-autonomous-automation", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp's docs describe multiple autonomous background automations — auto-receipt capture, invoice matching/coding/approval/payment, hotel rate monitoring with auto-rebooking, auto top-up with balance targets, and four dedicated AI agents handling coding, fraud, approvals, and payment end-to-end without manual triggering. This directly matches the story of AI-native background automation. Missing for 10: independent/hands-on verification that these automations run fully autonomously in production (community evidence only confirms manual card/expense workflows, not the autonomous agent features).", "evidenceIds": [ "ramp-docs-1", "ramp-docs-2", "ramp-docs-3", "ramp-docs-6", "ramp-docs-17" ] }, { "productId": "ramp", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp documents built-in AI agents that autonomously handle auto-coding, fraud prevention, approval routing, and payment, plus AI-powered intake and auto-categorization — evidence of task delegation to embedded AI. However, all evidence is vendor-sourced marketing copy with no independent/hands-on corroboration of an interactive assistant experience or how a user explicitly 'delegates' vs. the AI running fully automatically in the background. Missing for 10: independent user reports of interacting with/delegating to the assistant, detail on the assistant's conversational/task-delegation UX rather than automated background agents.", "evidenceIds": [ "ramp-docs-17", "ramp-docs-4", "ramp-docs-15", "ramp-docs-2" ] }, { "productId": "ramp", "storyId": "agentic-headless", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp provides a documented official CLI (ramp-cli) and a full REST/OpenAPI developer API plus machine-readable docs (llms.txt, llms-api.txt, openapi/developer-api.json), which together enable scripted/headless automation suitable for CI pipelines. However, there is no first-party or community evidence of actual CI usage, rate-limit guidance for automated pipelines, or examples of running the CLI unattended. Missing for 10: documented CI/CD integration examples, independent confirmation of headless CLI use in production pipelines, and details on authentication/rate limits for automated batch jobs.", "evidenceIds": [ "ramp-probe-3", "ramp-probe-1", "ramp-docs-9", "ramp-docs-10", "ramp-docs-11" ] }, { "productId": "ramp", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Ramp exposes its own official MCP server (ramp-probe-2) for others to connect to, but there is no evidence Ramp itself can act as an MCP client and plug in external MCP servers to extend its AI agents' toolset. Missing for 10: any documentation of Ramp's AI agents consuming external MCP servers, any client-side MCP configuration UI, or user guides for adding third-party MCP tool providers.", "evidenceIds": [ "ramp-probe-2", "ramp-docs-17" ] }, { "productId": "ramp", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp is a finance SaaS platform (not itself an agent), so shipping an official MCP server is a fair, applicable axis, and evidence confirms one exists at support.ramp.com/ramp-mcp alongside machine-readable LLM/API docs and an open API for connectivity. Missing for 10: detailed documentation of MCP server capabilities/tools, and independent/hands-on confirmation that the MCP server works as advertised.", "evidenceIds": [ "ramp-probe-2", "ramp-docs-9", "ramp-docs-12" ] }, { "productId": "ramp", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp publishes an official MCP server (support.ramp.com/ramp-mcp) plus llms.txt/CLI docs, which directly enables AI agents/assistants to operate Ramp via natural-language commands, and it also ships internal AI agents for coding/approval/payment automation. missing for 10: hands-on/independent evidence of a user actually issuing natural-language commands through the MCP server, and detail on what actions/scopes the MCP server exposes.", "evidenceIds": [ "ramp-probe-2", "ramp-probe-3", "ramp-docs-17", "ramp-docs-9" ] }, { "productId": "ramp", "storyId": "agentic-official-cli", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "A probe confirms an official CLI repo at github.com/ramp-public/ramp-cli, satisfying the core ask for an AI-native official CLI. Missing for 10: no first-party docs describing CLI features/usage in depth, no independent hands-on review or community corroboration of the CLI's capabilities.", "evidenceIds": [ "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Ramp publishes a documented public Developer API with OpenAPI spec, LLM-readable docs (/llms.txt, /llms-api.txt), and rate-limiting guides, confirmed by direct probes (200 OK) plus an official MCP server and CLI extending programmatic/AI-native access. Missing for 10: independent third-party developer reports of building against the API, and more detail on auth/scopes beyond the doc index.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-10", "ramp-docs-11", "ramp-probe-1", "ramp-probe-2", "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Ramp has a developer API, OpenAPI spec, and an official MCP server, so scoped credentialing is a fair capability to ask about for an API/agentic platform — but the evidence pack contains no mention of API keys, OAuth scopes, role-based permissions, or any mechanism to issue least-privilege credentials specifically for an AI agent.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "agentic-sdks", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Ramp provides a public developer API with OpenAPI spec, LLM-friendly docs (llms.txt/llms-api.txt), an official CLI, and an official MCP server, all of which let AI-native developers build against Ramp programmatically. However, no evidence of dedicated language SDKs (e.g. Python/Node client libraries) is present—only raw API/OpenAPI access plus CLI/MCP tooling. Missing for 10: official first-party SDK packages in specific languages, independent developer corroboration of SDK usage.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-10", "ramp-docs-11", "ramp-probe-1", "ramp-probe-2", "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack details Ramp's developer API, OpenAPI spec, MCP server, and CLI, but never mentions webhook subscriptions or event notifications anywhere. Webhooks are a plausible capability for a platform with a full developer API, so absence of evidence means this axis is unmet rather than inapplicable.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "ai-anomaly-spend-detection", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Ramp claims a dedicated AI 'fraud prevention' agent alongside auto-coding and dynamic, multi-department approval routing, which implies automated flagging of anomalous or out-of-policy transactions for review (ramp-docs-17, ramp-docs-16). However, there is no detailed documentation of how anomaly detection thresholds work, no explicit 'flag for review' workflow description, and no independent/hands-on evidence corroborating this specific capability. Missing for 10: detailed docs on anomaly/policy-violation detection logic, explicit reviewer workflow, and independent verification of fraud-flagging accuracy.", "evidenceIds": [ "ramp-docs-17", "ramp-docs-16", "ramp-docs-15" ] }, { "productId": "ramp", "storyId": "ai-bill-data-extraction", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp Bill Pay explicitly describes AI reading/matching vendor invoices, auto-coding to GL, PO matching, and routing for approval before payment, directly matching the AP auto-population-for-review story, backed by the four dedicated AI agents (auto-coding, fraud, routing, payment) and ERP sync docs. Missing for 10: independent hands-on verification of invoice-reading accuracy and no third-party review specifically confirming bill-reading AI performance.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-15", "ramp-docs-17", "ramp-docs-5" ] }, { "productId": "ramp", "storyId": "ai-books-close-automation", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp documents AI-driven auto-coding, auto-categorization, real-time bidirectional ERP sync eliminating manual journal entries, and dedicated AI agents for auto-coding/fraud/approvals/payments, directly targeting faster book closing; broad accounting integration list (NetSuite, QuickBooks, Sage Intacct, etc.) supports this at scale. Missing for 10: independent/hands-on verification of close-time reduction and no specific 'days to close' benchmark or customer-reported close-cycle metric.", "evidenceIds": [ "ramp-docs-5", "ramp-docs-15", "ramp-docs-17", "ramp-docs-2", "ramp-intdir-1" ] }, { "productId": "ramp", "storyId": "ai-contract-parsing-procurement", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp's docs explicitly state AI-powered intake parses contracts and screenshots to auto-populate procurement request forms, directly matching the story. Missing for 10: independent/hands-on corroboration of this specific contract-parsing feature and detail on accuracy/edge cases.", "evidenceIds": [ "ramp-docs-4", "ramp-docs-16" ] }, { "productId": "ramp", "storyId": "ai-gl-coding-automation", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp documents AI-driven auto-coding of transactions (auto-categorization based on transaction details/history/feedback, syncing to ERP) alongside a dedicated 'auto-coding' AI agent, multi-entity support with consolidated reporting, and real-time bidirectional ERP sync that eliminates manual journal entries — directly supporting cross-entity GL coding to accelerate close. Missing for 10: independent/hands-on evidence specifically validating GL-coding accuracy across multiple entities during a close cycle, and no third-party accounting-team testimonial on close-time reduction.", "evidenceIds": [ "ramp-docs-15", "ramp-docs-17", "ramp-docs-14", "ramp-docs-5", "ramp-docs-2" ] }, { "productId": "ramp", "storyId": "ai-price-monitoring-rebooking", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp's docs explicitly claim hotel rate monitoring with automatic rebooking when prices drop $50+, directly matching the story. Missing for 10: independent/hands-on corroboration of this specific feature and details on flight/other travel rate types beyond hotels.", "evidenceIds": [ "ramp-docs-3" ] }, { "productId": "ramp", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence confirms Ramp has an OpenAPI spec and machine-readable llms.txt/API docs for developers, but nothing indicates an interactive reference with runnable/try-it-now examples (e.g., a Swagger/Redoc-style console). Missing for 10: any mention of an interactive API console, live request execution, or embedded runnable code samples.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-10", "ramp-probe-1" ] }, { "productId": "ramp", "storyId": "api-machine-spec", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Ramp's developer docs explicitly expose a downloadable OpenAPI spec at /openapi/developer-api.json, confirmed by both documentation references and a live probe returning HTTP 200 at the llms.txt index that lists this spec alongside other machine-readable formats. Missing for 10: independent third-party confirmation that the OpenAPI file itself is complete/valid beyond the vendor's own docs.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-10", "ramp-probe-1" ] }, { "productId": "ramp", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence of a sandbox/test environment for developers or AI agents to safely test API/MCP calls without touching production financial data; docs only reference production API/MCP/CLI endpoints. Missing for 10: any mention of sandbox mode, test API keys, staging environment, or synthetic data support.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Ramp has a documented Developer API (OpenAPI spec, guides, rate-limiting docs) with a 'v1' path in the URL, but nowhere is there mention of a versioning scheme or a documented deprecation/sunset policy for API versions.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-11", "ramp-probe-1" ] }, { "productId": "ramp", "storyId": "application-status-tracking", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack describes an account application, review process, or status-tracking feature for founders during onboarding; all onboarding evidence relates to time-to-deploy after approval (e.g., ramp-docs-8), not application status tracking.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "auto-cash-topup-alerts", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp explicitly documents auto top-up from linked checking accounts with target balance automation and low-balance alerts, directly matching the story, but this rests on a single vendor claim with no independent/hands-on corroboration and no detail on multi-account 'treasury-yield' style cash optimization or yield features. missing for 10: independent verification of auto top-up working in practice, detail on interest/yield optimization across accounts, and community evidence confirming alert reliability.", "evidenceIds": [ "ramp-docs-6" ] }, { "productId": "ramp", "storyId": "auto-receipt-capture-on-swipe", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp's own docs claim auto-receipt capture at the moment of card swipe with AI-filled memos/categories, plus automatic categorization based on transaction details, history, and team feedback that syncs coded transactions to ERP — directly matching the story. Community evidence corroborates general ease-of-use of card issuance/expense flow, though no independent hands-on confirmation specifically of receipt auto-capture accuracy exists. Missing for 10: independent/hands-on verification of receipt-matching accuracy and edge cases (e.g., lost receipts, disputes).", "evidenceIds": [ "ramp-docs-1", "ramp-docs-15", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "automatic-invoice-followup", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Ramp's evidence describes accounts-payable automation (paying vendor bills, card spend, expense management) but contains no mention of Ramp issuing customer invoices or performing accounts-receivable collections/dunning; this is a different product category (AR/invoicing tools) rather than a gap in an applicable Ramp capability.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp exposes a public API, official CLI, and MCP server (ramp-probe-1/2/3) plus CSV export/import (ramp-docs-12) that would let an AI-native user script bulk actions, and AI agents already auto-code/categorize transactions at scale across the platform (ramp-docs-15, ramp-docs-17). However there's no direct evidence of a dedicated bulk-edit/bulk-approve UI or documented batch endpoints for acting on many items simultaneously. Missing for 10: explicit bulk-operation API endpoints or UI (bulk approve, bulk export, batch transaction updates) and independent confirmation these programmatic paths work for large-scale bulk actions.", "evidenceIds": [ "ramp-docs-15", "ramp-docs-17", "ramp-docs-12", "ramp-probe-1", "ramp-probe-2", "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp ships several built-in automations that fire actions on events—auto top-up triggered by low balance, hotel rate rebooking on price drops, dynamic approval routing, and AI agents auto-coding/paying invoices—showing real automation depth, and its public API/MCP/CLI let developers extend this. However these are largely preset, product-specific automations rather than a general user-defined rule engine (arbitrary trigger→condition→action authoring), and there's no evidence of a configurable rules/webhooks builder for custom event handling. Missing for 10: a documented custom rule-builder UI or webhook/event API for arbitrary automations, and independent confirmation of rule flexibility beyond the shipped presets.", "evidenceIds": [ "ramp-docs-3", "ramp-docs-6", "ramp-docs-16", "ramp-docs-17", "ramp-probe-2", "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Ramp ships specific built-in recurring automations (auto top-up with target-balance thresholds, hotel rate monitoring/rebooking, dynamic approval routing) that run continuously without user re-triggering, and exposes an API/MCP server/CLI that could be used to build custom scheduled jobs. However there's no evidence of a general-purpose workflow/job scheduler (e.g., cron-style triggers, custom recurring automation builder) that an AI-native user could configure via the API or MCP server themselves — the cited automations are fixed product features, not user-defined scheduled workflows. Missing for 10: documentation of a programmable scheduling/trigger API for arbitrary recurring jobs, evidence the MCP server or CLI supports defining custom recurring workflows, and independent confirmation of these automations working as advertised.", "evidenceIds": [ "ramp-docs-3", "ramp-docs-6", "ramp-docs-16", "ramp-docs-17", "ramp-probe-2", "ramp-probe-3" ] }, { "productId": "ramp", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of version history, review workflows, or rollback capability for Ramp's automations (approval rules, agent actions, categorization rules, etc.). The evidence covers what the automations do, but nothing about auditing, versioning, or reverting automation configurations/agent decisions.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "bank-verification-letter", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions account/routing numbers, bank verification letters, or any similar account-detail retrieval feature for Ramp accounts.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "bill-pay-approval-workflow", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Ramp documents bill upload (drag-and-drop invoices), automatic PO matching and GL coding, dynamic multi-department approval routing, and automated vendor payment (ramp-docs-2, ramp-docs-16, ramp-docs-17), corroborated by a positive hands-on community account of easy approval-to-payment workflows (ramp-comm-2). Missing for 10: independent third-party audit of the full bill-pay approval chain and more granular detail on rejection/exception handling in approvals.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-16", "ramp-docs-17", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "budget-based-spend-enforcement", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp docs reference multi-entity support with entity-level restrictions, dynamic approval routing, and card issuance controls, implying budget/spend-limit enforcement by department, but there is no explicit first-party documentation of setting a hard department/program budget cap with automatic enforcement (e.g., blocking spend once a budget threshold is reached) nor independent confirmation of this specific behavior. missing for 10: explicit documentation of budget-setting UI/API tying spend limits to departments/programs, evidence of automatic blocking/alerts when budgets are exceeded, and independent/hands-on confirmation of enforcement in practice.", "evidenceIds": [ "ramp-docs-14", "ramp-docs-16", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "card-spend-limits-controls", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Evidence shows employees can quickly spin up new cards with approval workflows (ramp-comm-2) and that Ramp supports entity-level restrictions and dynamic approval routing (ramp-docs-14, ramp-docs-16), implying some granular control, but there is no explicit documentation of setting per-card numeric spend limits or category/merchant-level restrictions per employee. missing for 10: explicit docs on per-card spend limit configuration, merchant/category-level card controls, and independent verification of granularity.", "evidenceIds": [ "ramp-docs-14", "ramp-docs-16", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "consolidate-point-solutions", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Ramp's docs and case studies directly support the story: unified spend/card, bill pay/AP automation, banking/treasury (auto top-up, balances), multi-entity consolidation, and explicit customer proof of consolidating tools (Studs replacing 4 tools, AIRCO fast onboarding vs 6 months). Community evidence corroborates real-world use for expense/card issuance and approvals, reinforcing the platform's breadth beyond marketing claims. Missing for 10: independent case studies verifying bill-pay/banking consolidation claims (not just card/expense), and more third-party evidence on multi-entity/ERP sync accuracy.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-6", "ramp-docs-7", "ramp-docs-8", "ramp-docs-14", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "dedicated-accounting-api", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp documents a dedicated Developer API with OpenAPI spec, machine-readable docs (llms.txt, llms-api.txt), and bidirectional ERP sync for accounting data (transactions, coding, GL sync), confirmed by a live probe showing the API docs endpoint is reachable. Missing for 10: no independent developer testimonial or hands-on confirmation of actual accounting-data CRUD via the API, and no detail on specific accounting endpoints/scopes.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-5", "ramp-docs-12", "ramp-probe-1", "ramp-docs-15" ] }, { "productId": "ramp", "storyId": "earn-yield-on-balances", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack mentions auto top-up from linked checking accounts and target balance automation, but there is no mention of Ramp offering interest/yield on operating cash balances held within Ramp itself, nor any treasury/yield product distinct from moving funds elsewhere.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "embedded-banking-no-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Ramp is a corporate card/expense management platform with a developer API for expense automation, not a Banking-as-a-Service provider that lets developers embed licensed banking accounts into their own products. This story targets BaaS providers, which is a different product category than Ramp's offering.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "fast-cross-border-transfer", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack addresses international money transfer or cross-border payment speed; Ramp's evidence covers cards, bill pay, ERP sync, and vendor integrations but nothing about sending money abroad or transfer time guarantees. missing for 10: any mention of international/cross-border wire or transfer capability, evidence of transfer speed, currency/FX support.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "fast-onboarding-switch", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp provides a concrete customer proof point (AIRCO: full onboarding in 1 week vs 6 months on prior platform) directly matching the story, plus general positive hands-on feedback about quick setup of cards/expenses. Missing for 10: independent third-party verification of onboarding timelines beyond vendor case studies, and detail on the actual onboarding process/steps for a new customer.", "evidenceIds": [ "ramp-docs-8", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "fdic-insurance-sweep", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows only auto top-up from a linked checking account with balance targets (ramp-docs-6), not a multi-bank sweep program for maximizing FDIC coverage; no mention of partner-bank sweep networks or FDIC insurance expansion anywhere in the pack.", "evidenceIds": [ "ramp-docs-6" ] }, { "productId": "ramp", "storyId": "fee-free-foreign-card-spend", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of foreign transaction fees, international card usage, currency conversion, or cash withdrawal abroad — only receipt capture, AP automation, ERP sync, and integrations are covered. Axis applies to a corporate card product, but nothing in the pack supports the specific claim about fee-free international spend/withdrawal.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "freeze-replace-card", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Ramp is a corporate card platform where freezing/replacing lost cards is a standard, expected capability, but no evidence item describes card freezing or replacement workflows — only card issuance speed (ramp-comm-2) and unrelated features (receipts, AP automation, bill pay, ERP sync) are covered. Missing for 10: any documentation or community mention of freezing a lost/stolen card, ordering a replacement, or related self-service card controls.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "gl-sync-erp", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp explicitly claims real-time bidirectional sync with ERPs eliminating manual journal entries, backed by auto-categorization and sync to ERP details, plus a broad list of supported ERP integrations (NetSuite, Sage Intacct, QuickBooks, etc.). Missing for 10: independent/hands-on verification of true bidirectional (not just push) sync and any community confirmation of eliminating manual JE work.", "evidenceIds": [ "ramp-docs-5", "ramp-docs-15", "ramp-intdir-1" ] }, { "productId": "ramp", "storyId": "high-yield-savings-subaccount", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Ramp documents auto top-up and target-balance automation with low-balance alerts (ramp-docs-6), which supports the 'automated transfer rules' part of the story, but no evidence explicitly confirms a high-yield savings sub-account or yield-bearing cash cushion feature. missing for 10: explicit high-yield/interest-bearing savings sub-account documentation, evidence of yield rates, and independent corroboration of treasury cash-cushion use case.", "evidenceIds": [ "ramp-docs-6" ] }, { "productId": "ramp", "storyId": "instant-virtual-card-issuance", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Community evidence confirms Ramp lets users spin up a new virtual/business expense card in under a minute for a specific purchase, supporting instant, purpose-scoped card creation. However, there's no direct first-party documentation explicitly describing vendor- or category-locked virtual card controls (e.g., merchant-lock, spend-category restrictions) beyond general references to approvals and multi-entity restrictions. Missing for 10: explicit docs on merchant/category-locking rules for virtual cards, admin UI screenshots/workflow for scoping a card to a single vendor or ad-spend category, and independent verification of that specific control granularity.", "evidenceIds": [ "ramp-comm-2", "ramp-docs-16", "ramp-docs-14" ] }, { "productId": "ramp", "storyId": "invoice-creation-collection", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Ramp's evidence covers expense management, bill pay/AP automation, procurement, and ERP sync, but there is no mention of creating or sending branded customer-facing invoices with payment collection (accounts receivable), which is a distinct capability from bill pay.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "lock-exchange-rate", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item mentions FX rate locking, forward contracts, or fixed-window exchange rate guarantees for international transfers; Ramp's evidence covers expense management, procurement, ERP sync, and integrations but nothing about currency rate hedging or locking.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "multi-currency-account-creation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers card issuance, expense automation, ERP sync, and integrations, but contains no mention of multi-currency account balances or FX holding capabilities. Multi-currency balance management is a fair axis for a corporate finance/spend platform, so absence of evidence yields 'none'.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "multi-currency-interest", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions multi-currency accounts, FX holding, or interest/yield on non-USD balances; Ramp evidence covers cards, expense automation, integrations and AI agents but nothing about earning interest on multi-currency balances. Missing for 10: any mention of multi-currency account support, interest/yield rates, or treasury/FX yield features.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "multiple-checking-subaccounts", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows only auto top-up from a single linked checking account to Ramp's card account with target-balance automation (ramp-docs-6), not the creation of multiple checking sub-accounts or auto-allocation of incoming deposits across them. Missing for 10: any mention of multiple sub-accounts, deposit-splitting/allocation rules, or treasury account structuring.", "evidenceIds": [ "ramp-docs-6" ] }, { "productId": "ramp", "storyId": "no-fee-card-cashback", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers expense automation, receipt capture, ERP sync, approvals, and AI agents, but contains no mention of cashback rewards or automatic cashback redemption on card spend anywhere in the docs or community evidence.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "one-click-payment-approval", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp docs describe dynamic approval routing across departments and one-click, AI-driven payment flows (vendor invoice matched, coded, routed for approval, and paid), plus AI agents that handle approval routing and automatic payment, implying configurable permissions for who can approve/send. Community evidence corroborates a fast, one-click approve-and-fund experience for expenses. However, there's no explicit documentation of granular permission-setting UI/roles specifically for designating which teammates can approve and send payments with one click. Missing for 10: explicit admin-permission configuration screens/roles documentation, and independent confirmation of one-click send-payment permission setup.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-16", "ramp-docs-17", "ramp-comm-2" ] }, { "productId": "ramp", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Ramp exposes a documented Developer API with OpenAPI spec, LLM-readable docs, an official MCP server, and even a public CLI, indicating broad programmatic access aligned with AI-native workflows. However, there is no explicit claim or evidence that every UI capability (e.g., hotel rebooking automation, contract intake AI, dynamic approval routing) is fully exposed via the API — only general API/ERP sync and CSV export mentions. Missing for 10: an explicit statement or independent verification of full feature parity between API and UI, and evidence covering advanced workflow features (approvals, travel, intake) being API-accessible.", "evidenceIds": [ "ramp-docs-9", "ramp-docs-12", "ramp-probe-1", "ramp-probe-2", "ramp-probe-3", "ramp-docs-15" ] }, { "productId": "ramp", "storyId": "openness-full-export", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Ramp explicitly supports custom CSV exports and an open API for connectivity, plus a documented OpenAPI spec and developer API, which gives users a path to extract their data in open formats. However, there is no evidence of a full data-portability/export-everything guarantee, no mention of standardized bulk export tooling for account closure, and no independent confirmation of completeness of exports. missing for 10: dedicated 'export all data and leave' documentation, evidence of open/standard format for full account export (not just transactions via API/CSV), independent verification of export completeness.", "evidenceIds": [ "ramp-docs-12", "ramp-docs-9", "ramp-probe-1" ] }, { "productId": "ramp", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Ramp is a closed-source SaaS fintech platform for expense/finance management; open-source source-code licensing is not a fair axis for this product category, unlike an SDK/framework/library.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Ramp is a SaaS fintech/expense-management platform delivered as a hosted service tied to banking, card issuing, and payment rails that cannot be self-hosted; self-hosting the core product is a category error for this kind of financial SaaS offering.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "physical-card-issuance", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Community evidence confirms Ramp lets a finance user quickly spin up a company card with approval and fund transfer, and docs mention entity-level restrictions and approval routing that imply role-based controls, but nothing explicitly confirms physical (vs. virtual) card issuance or granular role-based card permissions. Missing for 10: explicit mention of physical card issuance, and documentation of role-based spend controls/limits tied to employee roles.", "evidenceIds": [ "ramp-comm-2", "ramp-docs-14", "ramp-docs-16" ] }, { "productId": "ramp", "storyId": "po-matched-invoice-automation", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Ramp's docs directly describe the exact workflow: invoices dragged in are auto-matched to POs, auto-coded to GL, routed for approval, and paid, with dedicated AI agents for coding, approval routing, and payment execution. This is corroborated by ERP sync and categorization details, though evidence is entirely vendor-sourced with no independent hands-on validation of AP-specific matching accuracy. Missing for 10: independent/community confirmation of invoice-to-PO matching accuracy and edge-case handling.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-15", "ramp-docs-17", "ramp-docs-5", "ramp-docs-16" ] }, { "productId": "ramp", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses data residency, regional storage options, or compliance controls for choosing where data is stored; the evidence covers AI features, integrations, and MCP/API tooling only.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack item addresses AI-training data usage, opt-out controls, or privacy commitments regarding model training on customer data; the evidence covers product features, integrations, and MCP/CLI tooling only.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Ramp's evidence pack covers expense automation, AI agents, integrations, and MCP/API access, but there is no mention of data retention policies, deletion controls, or privacy configuration relevant to AI-native users. Nothing addresses how long data/prompts are stored or how users can delete data.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence exists of any telemetry/usage-tracking opt-out mechanism for AI features or product analytics; Ramp is explicitly a platform that tracks employee expenses/transactions as its core service, with no mention of an opt-out control for this tracking.", "evidenceIds": [ "ramp-comm-5" ] }, { "productId": "ramp", "storyId": "receipt-matching-by-email-upload", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Ramp's docs claim auto-receipt capture at swipe with AI-filled memos/categories, and automated matching/coding for vendor invoices dragged into the platform, which covers the core of automatic receipt-to-transaction matching via upload or email-based capture. Missing for 10: explicit documentation of the email-forwarding-to-transaction workflow specifically, and independent/hands-on confirmation of matching accuracy beyond vendor claims.", "evidenceIds": [ "ramp-docs-1", "ramp-docs-2", "ramp-docs-15" ] }, { "productId": "ramp", "storyId": "receive-multi-currency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Ramp's evidence pack covers cards, expense management, bill pay, ERP sync, and banking integrations, but nothing describes receiving inbound payments via local account details (e.g., local IBAN/ACH/SWIFT receiving accounts) in multiple currencies — this is a receivables/multi-currency collection capability not mentioned anywhere in the pack. Missing for 10: any mention of local currency receiving accounts, multi-currency invoicing/collections, or global payment-in details.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "request-limit-increase", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of a self-service screen for requesting card/transaction limit increases; only general card issuance and expense-tracking mentions appear (ramp-comm-2) but nothing about limit-increase requests.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "role-based-permissions", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Ramp docs mention multi-entity support with entity-level restrictions and dynamic approval routing across finance, IT, legal, and security, which implies some role/permission granularity across entities and departments, but there is no explicit documentation of a granular role/permission system covering locations and individual team members. missing for 10: dedicated documentation of role-based access control, granular permission settings per user/location/department, and independent corroboration of these controls.", "evidenceIds": [ "ramp-docs-14", "ramp-docs-16" ] }, { "productId": "ramp", "storyId": "send-domestic-ach-wire", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Ramp's docs describe vendor invoices being routed, approved, and 'paid' automatically via a dedicated payment AI agent, implying built-in bill-pay/payment execution, but no evidence explicitly confirms domestic ACH or wire rail support, transfer limits, or same-day options. Missing for 10: explicit mention of ACH/wire payment methods, processing times, and any independent confirmation that payments are actually disbursed via bank rails rather than just approval routing.", "evidenceIds": [ "ramp-docs-2", "ramp-docs-17", "ramp-docs-16" ] }, { "productId": "ramp", "storyId": "send-international-payments", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses international payments, local currency support, or FX fee transparency—only US-focused corporate card, expense, and AP automation features are documented.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "transfer-delivery-estimate", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence pack item mentions ACH/wire delivery time estimates or any pre-confirmation display of settlement dates for payments; evidence covers card capture, invoice matching, ERP sync, integrations, and dev tools, none of which touch payment delivery estimates.", "evidenceIds": [] }, { "productId": "ramp", "storyId": "universal-transaction-search", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence pack item describes a universal/global search bar spanning transactions, vendors, and cards, nor any 'jump straight into initiating a payment' from search results. The evidence covers auto-categorization, invoice matching, approval routing, and integrations, but nothing about a unified search UX.", "evidenceIds": [] }, { "productId": "relay", "storyId": "24-7-support-access", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Community reviews mention 'helpful customer support' generally, but no evidence specifies 24/7 or live/urgent support availability, response times, or channels (phone/chat). missing for 10: documentation of support hours/availability, urgent-issue escalation process, live-agent channel details, and independent verification of responsiveness during emergencies.", "evidenceIds": [ "relay-comm-2" ] }, { "productId": "relay", "storyId": "accounting-software-sync", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Relay's docs explicitly describe receipt capture, real-time categorization, and automatic syncing to accounting software (relay-docs-3), plus named integrations with QuickBooks Online and Xero for detailed transaction sync (relay-docs-19) and Plaid-based connections to apps like Expensify (relay-docs-20). Missing for 10: independent/hands-on verification of the accounting sync quality and no detail on reconciliation accuracy or setup friction reported by users.", "evidenceIds": [ "relay-docs-3", "relay-docs-19", "relay-docs-20" ] }, { "productId": "relay", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "There is direct probe evidence that Relay's support site serves a working llms.txt file at https://support.relayfi.com/llms.txt returning HTTP 200 with structured content describing the product, confirming an agent-oriented docs endpoint exists. Missing for 10: no evidence of broader agent-oriented documentation beyond this single file, no confirmation it covers full product surface, and no independent/community corroboration of agents actually using it.", "evidenceIds": [ "relay-probe-1" ] }, { "productId": "relay", "storyId": "agentic-ai-insights", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions AI-generated insights, suggestions, forecasting, or any AI/ML-driven analysis within Relay; all listed features are manual banking, transfer, invoicing, and card-management tools. missing for 10: any mention of AI-powered insights, anomaly detection, spend suggestions, or predictive analytics, first-party or independent corroboration of such a feature.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay offers rule-based automations that run without manual intervention — auto-transfers on deposit, percentage/dollar-based multi-account splits, multi-step approval rules, and recurring invoices (relay-docs-1, relay-docs-6, relay-docs-15, relay-docs-17, relay-docs-18) — which qualifies as background automation. However this is traditional banking rule automation, not AI/agent-driven decisioning, and community evidence notes manual execution is still required for many external payments (relay-comm-1). Missing for 10: any AI/LLM-based autonomous decision-making, agent-triggered actions, or evidence of automations beyond simple scheduled/rule-based transfers.", "evidenceIds": [ "relay-docs-1", "relay-docs-6", "relay-docs-15", "relay-docs-17", "relay-docs-18", "relay-comm-1" ] }, { "productId": "relay", "storyId": "agentic-builtin-assistant", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform; no evidence suggests it offers or could plausibly ship a built-in AI assistant for task delegation—this is outside its core banking/finance-ops product category.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-headless", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer tool or agent; running it headlessly/in CI is a category mismatch with no evidence of any API/CLI/automation runtime for such use.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-mcp-client", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform; MCP tool-plugging is not a relevant axis for this product category, and no evidence suggests it exposes or consumes MCP servers.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-mcp-server", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an AI agent or developer tool; connecting an agent via an official MCP server is outside its product category and not a fair axis to expect.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-nl-commands", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform with a standard app UI; the evidence pack shows only manual navigation flows (menus, screens like Accounts → Limits) and no natural-language command interface, chatbot, or agentic control surface. There is an llms.txt file which suggests machine-readability but not that end users can operate the product via natural language. Missing for 10: any evidence of a natural-language interface, chat-based commands, or AI assistant for operating the account.", "evidenceIds": [ "relay-probe-1", "relay-docs-7", "relay-docs-10" ] }, { "productId": "relay", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer tool or coding-related product; an official CLI for AI-native workflows is not a fair expectation for this product category.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-public-api", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of a documented public API for programmatic/agentic access; all evidence pertains to the banking product's manual UI features, integrations via Plaid/QuickBooks, and support docs, not an API for driving Relay programmatically. missing for 10: public API docs, authentication/reference, SDKs, or any mention of API endpoints.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-scoped-keys", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer/agent tooling product; issuing scoped API credentials for AI agents is outside its category — this is a wrong-axis question, not a missing feature.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-sdks", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer/API product; the evidence pack shows no SDK offering at all, and this is a category mismatch rather than a missing feature relevant to its product type.", "evidenceIds": [] }, { "productId": "relay", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform; no evidence anywhere in the pack mentions webhooks, event subscriptions, or any API-based notification system for developers/agents. Missing for 10: any webhook documentation, event types, subscription/callback mechanism, or API reference.", "evidenceIds": [] }, { "productId": "relay", "storyId": "ai-anomaly-spend-detection", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions AI-driven anomaly detection, fraud monitoring, or automated flagging of out-of-policy transactions; Relay's documented features are manual controls like spend limits, roles, and multi-step approval rules, not AI-based review triggers.", "evidenceIds": [] }, { "productId": "relay", "storyId": "ai-bill-data-extraction", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows bill upload, delegation, and approval automation (relay-docs-4) but nothing about AI reading bill contents to extract payment details for review — no OCR/AI-parsing capability is documented anywhere in the pack.", "evidenceIds": [] }, { "productId": "relay", "storyId": "ai-books-close-automation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Relay offers rule-based automation (auto-transfers, categorization, sync to QuickBooks/Xero) but there is no evidence of AI-driven automation specifically aimed at closing the books faster—no mention of AI reconciliation, AI-assisted month-end close, or similar. missing for 10: any AI-specific book-closing automation, evidence of month-end close acceleration, AI-powered reconciliation or reporting features.", "evidenceIds": [ "relay-docs-3", "relay-docs-19", "relay-docs-20" ] }, { "productId": "relay", "storyId": "ai-contract-parsing-procurement", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack of AI parsing vendor contracts or auto-populating procurement request forms; Relay's evidence covers banking, cards, invoicing, bill pay, and accounting sync but nothing about contract parsing or procurement workflows. missing for 10: any AI contract-parsing capability, any procurement request form feature, any evidence of document ingestion/AI extraction.", "evidenceIds": [] }, { "productId": "relay", "storyId": "ai-gl-coding-automation", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform whose evidence shows expense categorization and syncing to QuickBooks/Xero, but no mention of AI-driven GL code assignment across entities or multi-entity close acceleration. Missing for 10: any AI-based GL coding feature, multi-entity support, or close-acceleration workflow.", "evidenceIds": [ "relay-docs-3", "relay-docs-19" ] }, { "productId": "relay", "storyId": "ai-price-monitoring-rebooking", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking/cards-spend platform, not a travel booking or price-monitoring service; monitoring and rebooking travel rates is entirely outside its product category.", "evidenceIds": [] }, { "productId": "relay", "storyId": "api-interactive-docs", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer platform or API product; an 'interactive API reference with runnable examples' is not a fair capability to expect from this kind of product. No evidence suggests Relay exposes a public API or developer docs of that nature.", "evidenceIds": [] }, { "productId": "relay", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of an OpenAPI/Swagger spec or any machine-readable API documentation; evidence only covers banking features, support articles, and an llms.txt file (which is not an API spec).", "evidenceIds": [] }, { "productId": "relay", "storyId": "api-sandbox", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer/AI tool with a testable API or sandbox environment; no evidence pack items address sandbox/test environments for AI-native integration, and the concept of 'sandbox vs production data' is outside this product's category.", "evidenceIds": [] }, { "productId": "relay", "storyId": "api-versioning-policy", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not a developer API/platform product; the evidence pack contains no mention of a public API at all, versioned or otherwise. Versioned APIs with deprecation policies is a software-platform axis that doesn't apply to a banking product's consumer-facing feature set.", "evidenceIds": [] }, { "productId": "relay", "storyId": "application-status-tracking", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "relay-docs-12 directly confirms founders can check application status anytime from the homepage during the 1-2 business day review period, with email notification on decision. missing for 10: no independent/community corroboration of the status-checking UX itself, and no detail on what status states are shown.", "evidenceIds": [ "relay-docs-12" ] }, { "productId": "relay", "storyId": "auto-cash-topup-alerts", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay supports automated transfer rules between accounts by dollar amount or percentage (relay-docs-15) and cash-cushion/high-yield savings automation (relay-docs-6, relay-docs-24), corroborated by a community report of automatic money partitioning (relay-comm-1). However, there is no evidence of a specific 'low-balance alert' notification feature or threshold-triggered auto top-up logic. Missing for 10: explicit low-balance alert/notification capability, confirmation that transfers can be triggered by balance thresholds rather than just fixed schedules/percentages, independent verification of alerting reliability.", "evidenceIds": [ "relay-docs-15", "relay-docs-6", "relay-docs-24", "relay-comm-1" ] }, { "productId": "relay", "storyId": "auto-receipt-capture-on-swipe", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Relay's own docs state it can 'Capture receipts, categorize expenses in real time, and sync everything to your accounting software automatically' (relay-docs-3), directly matching the story, but there's no detail on the actual capture mechanism (e.g., automatic prompt at time of swipe vs. manual photo upload) and no independent or hands-on corroboration of this specific feature working seamlessly. Missing for 10: independent/community validation of the receipt-capture flow, technical detail on how capture is triggered at point-of-sale, and any evidence it truly requires zero manual entry.", "evidenceIds": [ "relay-docs-3", "relay-docs-2" ] }, { "productId": "relay", "storyId": "automatic-invoice-followup", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Relay's own marketing states invoicing lets you 'request payments... and let Relay handle the follow-up' and supports recurring invoices, directly claiming automated dunning for overdue invoices. However there's no detail on how follow-up scheduling/reminders work, no support-doc walkthrough, and no independent/community corroboration that this feature works as described in practice. missing for 10: detailed documentation of follow-up cadence/rules, hands-on or community validation of automated chasing actually reducing manual work.", "evidenceIds": [ "relay-docs-5", "relay-docs-11", "relay-docs-18" ] }, { "productId": "relay", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Relay offers some bulk-style automation — auto-transferring funds across up to 20 accounts, issuing up to 50 cards, multi-step approval rules, and bulk vendor bill uploads — but these are manual UI-driven configurations rather than a programmatic/bulk-API interface an AI-native user could drive across many items at once. Missing for 10: evidence of an API or agent-facing bulk operation endpoint, batch transaction processing, or CSV/bulk import-export capability confirmed by independent testing.", "evidenceIds": [ "relay-docs-14", "relay-docs-15", "relay-docs-16", "relay-docs-17", "relay-docs-4" ] }, { "productId": "relay", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay supports rule-based automation for money movement — auto-transferring deposits across accounts, percentage/dollar-based automated transfers, and multi-step approval rules — which satisfies a narrow slice of 'define rules that trigger actions on events.' However, these are fixed banking-specific triggers (deposits, thresholds, approvals) rather than a general-purpose, AI-native event/action framework (no webhooks, API-triggered rules, or custom event definitions are evidenced). Missing for 10: evidence of programmable/custom event triggers via API or webhooks, broader condition-action rule builder beyond transfers/approvals, and any AI-agent-facing automation interface.", "evidenceIds": [ "relay-docs-6", "relay-docs-15", "relay-docs-17", "relay-docs-1" ] }, { "productId": "relay", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Relay supports recurring financial automations like scheduled/percentage-based account transfers, recurring invoices, and automated approval rules, which count as recurring workflow scheduling within its banking domain. However there's no evidence of a general-purpose job/workflow scheduler, API/webhook triggers, or any AI-native automation surface for arbitrary tasks. Missing for 10: API-based scheduling, arbitrary workflow/job automation beyond money movement, AI-agent-facing scheduling interface.", "evidenceIds": [ "relay-docs-15", "relay-docs-18", "relay-docs-4", "relay-docs-17" ] }, { "productId": "relay", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an automation/workflow tool with version control, review, or rollback of automations — this axis is a category error for this product type.", "evidenceIds": [] }, { "productId": "relay", "storyId": "bank-verification-letter", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Relay's own support docs explicitly state that account/routing numbers can be viewed anytime under Accounts → Account Details, and a bank verification letter can be generated from the same screen, directly matching the story. Missing for 10: independent/hands-on community confirmation of this specific feature and detail on letter format/turnaround time.", "evidenceIds": [ "relay-docs-7" ] }, { "productId": "relay", "storyId": "bill-pay-approval-workflow", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Relay's docs directly support bill upload and vendor payment with approval workflows: relay-docs-4 explicitly states 'Upload bills, delegate tasks, automate approvals, and pay vendors the way they want to be paid,' and relay-docs-17 confirms 'Multi-step approval rules' as a product feature, matching the persona's need to route bills through approvals before paying vendors. Community evidence (relay-comm-1) corroborates that Relay handles money partitioning and payments, though notes manual execution steps for external payments. Missing for 10: independent hands-on review of the bill-approval workflow specifically (most community evidence focuses on account partitioning/cards rather than AP approval routing), and no detail on how many approval steps/roles are configurable.", "evidenceIds": [ "relay-docs-4", "relay-docs-17", "relay-comm-1" ] }, { "productId": "relay", "storyId": "budget-based-spend-enforcement", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay lets admins issue cards with set spend limits, define roles, and separate funds into up to 20 checking accounts (useful as informal department/program buckets) with automated transfer rules, and 'multi-step approval rules' are mentioned on the pricing page. However there's no explicit 'budget' object with rolling caps per department/program beyond individual card limits, and community reviews note 'problems with prescribed limits,' suggesting enforcement isn't perfectly reliable. Missing for 10: a dedicated budget-creation feature (vs just card limits/accounts), documented department-level aggregate spend caps, and clear evidence enforcement is robust in practice.", "evidenceIds": [ "relay-docs-2", "relay-docs-15", "relay-docs-17", "relay-comm-2", "relay-comm-4" ] }, { "productId": "relay", "storyId": "card-spend-limits-controls", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Relay's docs confirm card issuance with spend limits, role definitions, real-time transaction tracking, and multi-step approval rules (relay-docs-2, relay-docs-16, relay-docs-17), directly supporting granular per-card controls for employees. However, community reviews note occasional 'problems with prescribed limits' and permission glitches (relay-comm-2), and hard caps like a $7,000 daily card limit (relay-comm-4) suggest some inflexibility. Missing for 10: deeper documentation on category/merchant-level restrictions, audit trails for limit changes, and independent confirmation that granular controls work flawlessly at scale.", "evidenceIds": [ "relay-docs-2", "relay-docs-16", "relay-docs-17", "relay-comm-2", "relay-comm-4" ] }, { "productId": "relay", "storyId": "consolidate-point-solutions", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Relay documents an all-in-one platform combining multiple checking/savings accounts, cards with spend controls, bill pay with approvals, invoicing/receivables, receipt capture, and accounting sync (QuickBooks/Xero), directly replacing separate spend management, bill pay, and banking tools, and community reviews corroborate the multi-account and interest features in real use. missing for 10: independent case studies explicitly confirming founders consolidated away from other named point solutions, and more hands-on verification of bill pay/invoicing depth beyond docs and one HN mention.", "evidenceIds": [ "relay-docs-1", "relay-docs-2", "relay-docs-3", "relay-docs-4", "relay-docs-5", "relay-docs-6", "relay-docs-19", "relay-comm-1", "relay-comm-2" ] }, { "productId": "relay", "storyId": "dedicated-accounting-api", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows Relay syncing transaction data into QuickBooks/Xero and Plaid-based app connections, but there is no mention of a developer-facing API to view or manage accounting data programmatically. Missing for 10: any public API docs, endpoints, authentication, or SDK for accounting data access.", "evidenceIds": [ "relay-docs-19", "relay-docs-20" ] }, { "productId": "relay", "storyId": "earn-yield-on-balances", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Relay offers built-in high-yield savings accounts (up to 3.00% APY) that automatically pull idle operating cash into yield-bearing accounts within the same platform, and community evidence corroborates that tax/reserve balances earn extra interest without moving funds elsewhere. missing for 10: independent verification of actual APY competitiveness/consistency over time, and clearer detail on withdrawal friction or limits on savings-account access for operating cash.", "evidenceIds": [ "relay-docs-6", "relay-docs-24", "relay-comm-1" ] }, { "productId": "relay", "storyId": "embedded-banking-no-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a direct-to-business neobank/banking app for SMBs, not a Banking-as-a-Service or embedded-finance platform that developers can white-label into their own products; none of the evidence mentions an API, SDK, or licensing partnership for embedding accounts into third-party apps. This story targets BaaS providers, which is a different product category than Relay's offering.", "evidenceIds": [] }, { "productId": "relay", "storyId": "fast-cross-border-transfer", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows Relay wires (domestic and international) can send 'same-day' at best, and ACH takes 1-3 business days — nothing supports transfers arriving in under a minute. The axis applies since cross-border payments are a core banking feature, but no evidence of near-instant delivery exists.", "evidenceIds": [ "relay-docs-9", "relay-docs-23", "relay-comm-5" ] }, { "productId": "relay", "storyId": "fast-onboarding-switch", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay shows a fast application review (1-2 business days per relay-docs-12) and easy setup of accounts, cards, and invoicing, suggesting quick onboarding, but there's no explicit evidence of an end-to-end 'week-long' onboarding timeline or migration process from another bank. missing for 10: documented full onboarding timeline/case study, evidence of migrating existing banking relationships/data within a week, independent confirmation of onboarding speed beyond application approval.", "evidenceIds": [ "relay-docs-12", "relay-docs-7", "relay-docs-1", "relay-comm-2" ] }, { "productId": "relay", "storyId": "fdic-insurance-sweep", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Relay lets users open multiple checking accounts and automate internal transfers between them (Profit First style) and offers high-yield savings, but there is no mention of a multi-bank sweep network or expanded FDIC coverage across partner banks. missing for 10: any documentation of an FDIC sweep program, partner bank network, or expanded insurance coverage mechanism.", "evidenceIds": [ "relay-docs-1", "relay-docs-14", "relay-docs-15", "relay-docs-24" ] }, { "productId": "relay", "storyId": "fee-free-foreign-card-spend", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence covers Relay's domestic checking, cards, invoicing, and international wire transfers (with a $10 fee), but nowhere states or documents that its Visa debit/credit cards have no foreign transaction fees or how cash withdrawals abroad are priced. This is a fair question for a business card product, but no first-party or community evidence confirms fee-free foreign card spend/withdrawal.", "evidenceIds": [ "relay-docs-2", "relay-docs-23", "relay-comm-5" ] }, { "productId": "relay", "storyId": "freeze-replace-card", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "relay-docs-8 directly documents freezing a card instantly in-app and ordering a replacement (5–7 business days), matching the story exactly, with community reviews (relay-comm-2) corroborating a functional, user-friendly card management experience. Missing for 10: independent hands-on confirmation specifically of the freeze/replace flow (vs general app usability).", "evidenceIds": [ "relay-docs-8", "relay-docs-2", "relay-comm-2" ] }, { "productId": "relay", "storyId": "gl-sync-erp", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Relay documents syncing transaction data into QuickBooks Online and Xero (relay-docs-19) and categorizing expenses in real time (relay-docs-3), which reduces manual entry, but this is one-way transaction sync into small-business accounting software, not bidirectional sync with an ERP system replacing journal entries. Missing for 10: evidence of true ERP (e.g., NetSuite/SAP) integration, bidirectional sync (journal entries flowing back), and any independent confirmation of 'real-time' accuracy beyond marketing copy.", "evidenceIds": [ "relay-docs-19", "relay-docs-3", "relay-docs-20" ] }, { "productId": "relay", "storyId": "high-yield-savings-subaccount", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Relay explicitly offers high-yield savings accounts (up to 3.00% APY) plus automated rules to move idle cash from operating accounts into savings, directly matching the story, and community evidence corroborates automated partitioning with interest earned on set-aside funds. Missing for 10: independent verification of actual APY rates achieved and hands-on testing of the automation rule reliability specifically for savings sweeps.", "evidenceIds": [ "relay-docs-6", "relay-docs-24", "relay-docs-15", "relay-comm-1" ] }, { "productId": "relay", "storyId": "instant-virtual-card-issuance", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay supports issuing multiple virtual/physical Visa cards with spend limits and role-based controls (relay-docs-2, relay-docs-16), which enables purpose-scoped cards for things like a vendor or ad spend, but there's no evidence of instant creation flows, per-card vendor/merchant-locking, or category-specific restrictions tailored to 'ad spend' style use cases. missing for 10: evidence of instant/quick card issuance UX, vendor-lock or merchant-category restriction features, and independent confirmation of ease/speed of scoped card creation.", "evidenceIds": [ "relay-docs-2", "relay-docs-16", "relay-docs-10" ] }, { "productId": "relay", "storyId": "invoice-creation-collection", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Relay's docs explicitly describe building and sending branded invoices with built-in payment collection ('no separate tool needed'), plus flexible payment options, automated follow-up, and recurring invoices as a feature tier. Missing for 10: independent/hands-on community corroboration of invoicing feature usage and details on branding customization depth.", "evidenceIds": [ "relay-docs-5", "relay-docs-11", "relay-docs-18" ] }, { "productId": "relay", "storyId": "lock-exchange-rate", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a US business banking platform focused on domestic accounts, cards, invoicing, and bill pay; there's no evidence of FX/multi-currency transfer functionality or rate-locking, and international transfers appear to be simple wire-style payments rather than currency exchange. FX rate-locking is not a feature category this product addresses.", "evidenceIds": [] }, { "productId": "relay", "storyId": "multi-currency-account-creation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Relay's evidence describes opening up to 20 checking accounts and receiving/sending international wires, but all of these appear to be USD sub-accounts for organizing cash, not accounts that hold balances in multiple currencies (e.g., EUR, GBP) simultaneously. No evidence pack item describes multi-currency balance holding or FX conversion features.", "evidenceIds": [ "relay-docs-1", "relay-docs-14", "relay-docs-23", "relay-comm-5" ] }, { "productId": "relay", "storyId": "multi-currency-interest", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Relay's evidence shows only USD-based high-yield savings (up to 3.00% APY) and international wire transfers, but no support for holding balances in multiple currencies or earning interest on non-USD balances. Missing for 10: multi-currency account support, evidence of interest-bearing balances in currencies other than USD.", "evidenceIds": [ "relay-docs-24", "relay-docs-23" ] }, { "productId": "relay", "storyId": "multiple-checking-subaccounts", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Relay's docs clearly support opening up to 20 checking sub-accounts (including Profit-First style nicknaming) and automating transfers across them by dollar amount or percentage, and community evidence corroborates the auto-partitioning behavior in practice. missing for 10: independent verification of allocation reliability/edge cases (e.g., failed or delayed auto-transfers) and more detail on configuring percentage-based rules beyond marketing copy.", "evidenceIds": [ "relay-docs-1", "relay-docs-14", "relay-docs-15", "relay-comm-1", "relay-probe-1" ] }, { "productId": "relay", "storyId": "no-fee-card-cashback", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence covers card issuance, spend limits, savings APY, and expense tracking, but nothing in the pack mentions cashback rewards on card spend at all. missing for 10: any mention of cashback program, rewards rate, or automatic redemption on Relay cards.", "evidenceIds": [] }, { "productId": "relay", "storyId": "one-click-payment-approval", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Relay docs mention 'automate approvals' and 'define roles' for teammates, and pricing page lists 'Multi-step approval rules' as a feature, supporting configurable approval permissions for payments. However, there's no detailed documentation on the one-click approve/send UX for designated approvers, and community reviews note some users experienced 'issues with permissions,' suggesting occasional friction. Missing for 10: explicit description of one-click approve/send workflow, detailed permission granularity (e.g., approval thresholds per teammate), and hands-on confirmation the feature works smoothly.", "evidenceIds": [ "relay-docs-4", "relay-docs-17", "relay-docs-2", "relay-comm-2" ] }, { "productId": "relay", "storyId": "openness-api-parity", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item mentions a public API, developer platform, or programmatic access to Relay's banking features; all evidence describes UI/app-based workflows (mobile app, web app screens) with no API documentation or endpoints referenced.", "evidenceIds": [] }, { "productId": "relay", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform; nothing in the evidence pack mentions bulk data export in open formats (CSV/JSON/OFX) or account portability/closure workflows for users to 'leave' with their data. Accounting sync (relay-docs-3) implies data transfer to third-party software but is not documented as a user-controlled full data export/exit mechanism.", "evidenceIds": [ "relay-docs-3" ] }, { "productId": "relay", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking/fintech product, not open-source software; open-licensed source code is not an applicable axis for this category.", "evidenceIds": [] }, { "productId": "relay", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a cloud business-banking SaaS platform, not open-source software or a deployable product; self-hosting is a category error for a regulated banking service with no evidence of any deployable core.", "evidenceIds": [] }, { "productId": "relay", "storyId": "physical-card-issuance", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Docs explicitly state issuing Visa debit or credit cards with defined roles and spend limits, real-time tracking (relay-docs-2), physical/virtual card issuance up to 50 cards (relay-docs-16), and card freeze/replacement management (relay-docs-8). Community evidence corroborates card limits and permissions in practice (relay-comm-4, relay-comm-2). Missing for 10: independent hands-on verification of role-based permission granularity and credit card specifics beyond marketing copy.", "evidenceIds": [ "relay-docs-2", "relay-docs-16", "relay-docs-8", "relay-comm-4", "relay-comm-2" ] }, { "productId": "relay", "storyId": "po-matched-invoice-automation", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Relay's evidence shows bill upload, approval routing, and vendor payment (relay-docs-4, relay-docs-17), but nothing about matching invoices to purchase orders or automated GL/expense coding tied to POs — a specific three-way-match AP capability that is absent from all docs and community sources.", "evidenceIds": [ "relay-docs-4", "relay-docs-17" ] }, { "productId": "relay", "storyId": "privacy-data-residency", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an AI/data-processing product; data residency/region choice is not an applicable axis for its category and no evidence pack item addresses AI-native data storage location controls.", "evidenceIds": [] }, { "productId": "relay", "storyId": "privacy-no-training", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an AI product with model-training data policies; this axis is a category error for this kind of product.", "evidenceIds": [] }, { "productId": "relay", "storyId": "privacy-retention-controls", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an AI system or data-processing tool; data retention/deletion controls for AI-native privacy posture is a category mismatch — this axis targets AI/data products, not banking services.", "evidenceIds": [] }, { "productId": "relay", "storyId": "privacy-telemetry-optout", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Relay is a business banking platform, not an AI tool/agent with telemetry settings relevant to AI-native usage; this axis is a category error for this product type.", "evidenceIds": [] }, { "productId": "relay", "storyId": "receipt-matching-by-email-upload", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay's marketing docs mention capturing receipts and categorizing expenses in real time with sync to accounting software, implying some auto-matching capability, but there is no evidence of an email-in receipt feature or detailed matching logic to specific transactions. missing for 10: explicit email-to-receipt ingestion method, confirmation that receipts are auto-matched to the correct transaction, and independent/hands-on verification of this workflow.", "evidenceIds": [ "relay-docs-3" ] }, { "productId": "relay", "storyId": "receive-multi-currency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Relay is a US business banking platform offering USD checking accounts and the ability to receive international wires into those accounts (relay-docs-13, relay-docs-23), but there is no evidence of local account details (e.g., IBAN/sort code equivalents) issued in multiple currencies for receiving payments locally in each currency, which is what this story requires.", "evidenceIds": [ "relay-docs-13", "relay-docs-23", "relay-docs-9" ] }, { "productId": "relay", "storyId": "request-limit-increase", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "First-party support docs explicitly describe a self-service flow: view current limits under Accounts → Limits and request an increase directly from that screen, with related help articles confirming the limits view. This matches the finance-lead story closely. Missing for 10: independent/hands-on confirmation that limit-increase requests are actually approved smoothly (one community review vaguely mentions 'problems with prescribed limits'), and no explicit persona-specific (finance-lead role) detail.", "evidenceIds": [ "relay-docs-10", "relay-docs-22", "relay-comm-2" ] }, { "productId": "relay", "storyId": "role-based-permissions", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Relay documents role definition, card-level spend limits, and multi-step approval rules (relay-docs-2, relay-docs-17), which supports basic team permissioning, but there's no evidence of granular controls segmented by location or department, nor detailed role-based access management. A community review also notes 'issues with permissions' as a minor complaint (relay-comm-2), suggesting the feature isn't fully robust in practice. Missing for 10: department/location-level permission scoping, audit trail of permission changes, and independent confirmation that role granularity works reliably at scale.", "evidenceIds": [ "relay-docs-2", "relay-docs-17", "relay-comm-2" ] }, { "productId": "relay", "storyId": "send-domestic-ach-wire", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Relay's docs explicitly describe paying vendors via ACH and wire, with delivery estimates (1-3 days ACH, same-day wires), bill upload/approval workflows, and limit management, and community evidence confirms these payments work in practice (with the caveat that execution is manual, not autonomous). Pricing tiers also confirm faster ACH is available on Pro plan. Missing for 10: independent hands-on verification of wire payment success/reliability at scale, more detail on wire fees/limits.", "evidenceIds": [ "relay-docs-4", "relay-docs-9", "relay-docs-10", "relay-comm-1", "relay-comm-3" ] }, { "productId": "relay", "storyId": "send-international-payments", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Relay supports sending and receiving international wires (docs-9, docs-23) with a clear $10 fee disclosed and waived on Pro plan (relay-comm-5), giving some fee transparency, but there is no evidence of actual local-currency disbursement, FX rate handling, or multi-currency accounts — wires appear to be standard bank wires, not localized payouts. Missing for 10: local currency payment execution, FX rate transparency, multi-currency support evidence, independent confirmation of international payment reliability.", "evidenceIds": [ "relay-docs-9", "relay-docs-23", "relay-comm-5" ] }, { "productId": "relay", "storyId": "transfer-delivery-estimate", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "relay-docs-9 explicitly states ACH takes 1–3 business days, wires can send same-day, and that users see the exact delivery estimate before confirming a transfer — directly matching the story. Missing for 10: independent/hands-on confirmation (e.g. screenshot or user report) of the pre-confirmation estimate UI beyond first-party support docs.", "evidenceIds": [ "relay-docs-9" ] }, { "productId": "relay", "storyId": "universal-transaction-search", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions a universal/global search bar that spans transactions, vendors, and cards, nor any workflow for jumping from search results into initiating a payment; the docs describe discrete screens (Accounts, Cards, Invoices, Limits) rather than a unified search experience. missing for 10: any mention of a search feature, cross-entity search UI, or search-to-payment flow.", "evidenceIds": [] }, { "productId": "wise", "storyId": "24-7-support-access", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of live/24-7 customer support access; instead community reports describe support taking 30 days to respond to urgent account issues and accounts being blocked without quick resolution, suggesting no reliable live urgent support channel.", "evidenceIds": [ "wise-comm-5", "wise-comm-6" ] }, { "productId": "wise", "storyId": "accounting-software-sync", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence covers payments, currency accounts, and cards, but nothing mentions accounting software sync (e.g. QuickBooks/Xero integrations) or automatic expense syncing; no such integration is documented in this evidence pack.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "A direct probe confirms llms.txt is live at docs.wise.com/llms.txt returning HTTP 200 with structured agent-oriented content describing the Global Payments API, showing an AI agent can be pointed at this file successfully. Missing for 10: independent/community confirmation of agents actually consuming it, and a discoverable OpenAPI spec (all candidate paths 404) to complement the llms.txt for deeper agentic use.", "evidenceIds": [ "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-ai-insights", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking product; there is no evidence of AI-generated insights or suggestions from user data within the product. This capability is not a fair expectation of a payments platform's core product category, making it an off-axis question for this type of product.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-autonomous-automation", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a financial/payments platform, not an automation/agent platform; setting up autonomous background automations is a category error for this product type. Evidence only shows payments API and account features, not workflow automation orchestration.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-builtin-assistant", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking product, not an AI assistant platform; no evidence pack item mentions any built-in AI assistant. Delegating tasks to a built-in AI assistant is a category error for this type of product.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-headless", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Wise documents an API for making business payments programmatically (wise-docs-6) and an llms.txt referencing a 'Global Payments API' (wise-probe-1), suggesting some headless/automation capability exists. However, no OpenAPI/swagger spec is discoverable at standard locations (wise-probe-2 shows 404s), and there is no explicit mention of CI integration, SDKs, webhooks, or automation-friendly tooling. Missing for 10: discoverable API spec, CI/CD examples, SDK/CLI tooling, and any explicit automation-focused documentation.", "evidenceIds": [ "wise-docs-6", "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-mcp-client", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a fintech/payments platform, not an AI agent or agent-hosting product; MCP-server plug-in capability is not a relevant axis for this kind of product and no evidence suggests otherwise.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-mcp-server", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a fintech/payments platform, not an AI agent; no evidence of an official MCP server being offered, and this is a fair 'none' vs 'na' distinction—since Wise is not itself an agent, the axis would apply if evidence existed, but nothing in the pack even hints at an MCP server offering (only an API and llms.txt probe).", "evidenceIds": [ "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-nl-commands", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking product, not a conversational or agentic interface; natural-language command operation is a category error for this type of product and no evidence suggests otherwise.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a financial/payments platform, not a developer tool or coding agent; an official CLI for AI-native workflows is not a category-appropriate axis, and no evidence suggests one exists.", "evidenceIds": [] }, { "productId": "wise", "storyId": "agentic-public-api", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Wise publishes public API docs (docs.wise.com) explicitly covering account creation, global payments, and business payments via API, and the llms.txt probe confirms a 'Global Payments API' surface. Missing for 10: a discoverable OpenAPI/swagger spec (all probed endpoints 404'd) and independent developer corroboration of API usage/reliability.", "evidenceIds": [ "wise-docs-6", "wise-docs-1", "wise-docs-2", "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of scoped or least-privilege API credential issuance (e.g., token scoping, permission granularity, or per-agent API keys); docs mention API payments but nothing about credential scoping mechanisms, and OpenAPI/spec probes 404.", "evidenceIds": [ "wise-docs-6", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Wise has business payment APIs and docs (wise-docs-6, wise-probe-1) but nothing about official SDKs/client libraries for developers; the OpenAPI spec itself 404s across all standard paths (wise-probe-2), suggesting even machine-readable API definitions aren't published, let alone language SDKs.", "evidenceIds": [ "wise-docs-6", "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions webhooks or event subscription capabilities for Wise Business; the docs cover payments, accounts, and cards but nothing about webhook subscriptions or event-driven notifications.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-anomaly-spend-detection", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of AI-driven anomaly detection or policy-based transaction flagging in Wise Business docs or community reports; evidence covers payments, cards, and account changes only. missing for 10: any AI/ML anomaly detection feature, policy rule engine, automated flagging or review workflow.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-bill-data-extraction", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking platform, not an AI document-processing tool; no evidence of bill-reading or OCR/AI invoice-extraction capability is claimed or implied, and this is outside its product category rather than a gap it fails at.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-books-close-automation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence covers cross-border payments, multi-currency accounts, and API access for payments, but nothing about AI-driven automations, bookkeeping/close-the-books workflows, or accounting integrations that speed up month-end close.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-contract-parsing-procurement", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking platform; AI-driven contract parsing to auto-populate procurement forms is a document-intelligence/procurement-software capability entirely outside its product category.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-gl-coding-automation", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/money-transfer platform, not an accounting/ERP system; GL coding and close-acceleration are accounting-software functions outside its category, and no evidence suggests it performs this role.", "evidenceIds": [] }, { "productId": "wise", "storyId": "ai-price-monitoring-rebooking", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a money transfer/multi-currency account and card platform; it has no travel booking or fare-tracking functionality, so monitoring/rebooking travel rates is a category error for this product.", "evidenceIds": [] }, { "productId": "wise", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of an interactive API reference with runnable examples; probes for OpenAPI/swagger specs all returned 404, and docs pack only lists feature descriptions, not interactive tooling.", "evidenceIds": [ "wise-probe-2" ] }, { "productId": "wise", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Wise Business exposes a documented API (payments, accounts, cards) so an OpenAPI-style machine-readable spec is a fair expectation, but direct probes for openapi.json/swagger.json and related paths all returned 404, and no evidence shows a downloadable spec elsewhere.", "evidenceIds": [ "wise-probe-2", "wise-docs-6" ] }, { "productId": "wise", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions a sandbox or test environment for Wise Business API testing; documentation focuses on live payment features, account creation, and API usage without any sandbox/test-mode reference. missing for 10: mention of sandbox environment, test API keys, or non-production testing mode.", "evidenceIds": [] }, { "productId": "wise", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of API versioning scheme or a documented deprecation policy; OpenAPI spec probes all returned 404, and community evidence actually shows abrupt, undocumented breaking changes (bank account details changing with zero notice) rather than a managed deprecation process.", "evidenceIds": [ "wise-probe-2", "wise-comm-2", "wise-comm-3", "wise-comm-5" ] }, { "productId": "wise", "storyId": "application-status-tracking", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack describes an application status tracker or onboarding review dashboard for founders; evidence covers payments, currencies, cards, and unrelated account-closure/support issues.", "evidenceIds": [] }, { "productId": "wise", "storyId": "auto-cash-topup-alerts", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of auto top-up between accounts or low-balance alert features; evidence covers multi-currency accounts, payments, cards, and rate locking but nothing about automated cash management/treasury alerting.", "evidenceIds": [] }, { "productId": "wise", "storyId": "auto-receipt-capture-on-swipe", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence Wise offers receipt capture, OCR, or expense coding features tied to card transactions; documentation only covers accounts, payments, and card issuance, not receipt automation.", "evidenceIds": [ "wise-docs-4", "wise-docs-6" ] }, { "productId": "wise", "storyId": "automatic-invoice-followup", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/money-transfer product, not an invoicing or accounts-receivable platform; automated invoice chasing/follow-up is outside its category and not a fair axis to evaluate.", "evidenceIds": [] }, { "productId": "wise", "storyId": "automation-bulk-operations", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence covers single-payment API and account features but nothing about batch/bulk payment operations, CSV uploads, or multi-item transaction processing that would support AI-native bulk automation.", "evidenceIds": [] }, { "productId": "wise", "storyId": "automation-rules-engine", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence of any rules engine, event-trigger system, or automation/workflow configuration in Wise Business docs; evidence only covers payments, accounts, cards, and API basics, not event-driven automation.", "evidenceIds": [] }, { "productId": "wise", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of scheduling recurring jobs/workflows or automation orchestration capability; the API docs only cover one-off payments, account creation, and currency exchange, with no mention of recurring/scheduled transfers or workflow automation.", "evidenceIds": [] }, { "productId": "wise", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking platform, not an automation-building tool; version control, review, and rollback of 'automations' is not a relevant category axis for this product's type.", "evidenceIds": [] }, { "productId": "wise", "storyId": "bank-verification-letter", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Wise documents providing 'global account details' for receiving payments (wise-docs-9), which supports viewing account/routing numbers, but there is no evidence of a dedicated bank verification letter generation feature. Additionally, community reports show account/routing numbers can change without warning (wise-comm-2, wise-comm-3, wise-comm-5), undercutting the 'anytime' reliability implied by the story. Missing for 10: documented bank verification letter/document generation tool, and confirmation that account numbers remain stable enough to be trusted 'anytime'.", "evidenceIds": [ "wise-docs-9", "wise-comm-2", "wise-comm-3", "wise-comm-5" ] }, { "productId": "wise", "storyId": "bill-pay-approval-workflow", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of bill upload, invoice capture, or approval workflow features in Wise Business; documentation covers payments, currency accounts, cards, and API for sending money, not AP bill approval routing.", "evidenceIds": [] }, { "productId": "wise", "storyId": "budget-based-spend-enforcement", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of department/program budgeting or automated spend-limit enforcement in Wise Business docs; evidence covers payments, currency accounts, and card issuance only, with community reports focused on account-number changes and account blocks, not budget controls.", "evidenceIds": [] }, { "productId": "wise", "storyId": "card-spend-limits-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence pack only mentions issuing debit cards worldwide (wise-docs-4) but contains no documentation of per-card spend limits, granular employee-level controls, or admin card management features. No evidence supports this specific capability.", "evidenceIds": [] }, { "productId": "wise", "storyId": "consolidate-point-solutions", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Wise Business clearly consolidates banking (multi-currency accounts, global payment details), cards, and payment sending/API into one platform, which covers 'banking' and part of 'spend'. However, there is no evidence of dedicated bill-pay/AP automation or spend-management features (approvals, budgets, expense categorization) that founders would need to fully replace those point solutions, and community reports show operational friction (account detail changes, account blocks) that undercut a seamless 'one platform' story. Missing for 10: dedicated bill pay/invoicing workflow, spend management/approval controls, and independent evidence of reliability at scale.", "evidenceIds": [ "wise-docs-1", "wise-docs-3", "wise-docs-4", "wise-docs-6", "wise-docs-9", "wise-comm-3", "wise-comm-6" ] }, { "productId": "wise", "storyId": "dedicated-accounting-api", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Wise exposes a documented 'Global Payments API' for sending/receiving money and business payments (wise-docs-6, wise-probe-1), which could be used to pull transaction/account data for accounting purposes, but there is no explicit documentation of endpoints for statements, balance history, or accounting-specific data management, and no OpenAPI spec is discoverable (wise-probe-2 shows 404s). Missing for 10: explicit accounting-data endpoints (statements, categorization, reconciliation), formal API reference/OpenAPI spec, and independent developer corroboration of using the API for accounting integration.", "evidenceIds": [ "wise-docs-6", "wise-probe-1", "wise-probe-2" ] }, { "productId": "wise", "storyId": "earn-yield-on-balances", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence in the pack mentions interest, yield, or return on operating cash balances held in Wise Business accounts; only FDIC pass-through insurance and payments/currency features are documented.", "evidenceIds": [ "wise-docs-11", "wise-docs-1", "wise-docs-9" ] }, { "productId": "wise", "storyId": "embedded-banking-no-license", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Wise's own docs explicitly claim businesses without financial licenses can offer accounts to their customers, backed by supporting account/currency/card issuance and FDIC passthrough features. However, this is entirely first-party marketing/docs with no independent case study confirming a developer actually embedding Wise accounts for end customers, and community reports show real operational risk (a Wise Business account being fully blocked over category mismatch, and account details changing with no notice) that could undermine trust in offering these as a foundation for customer-facing banking. missing for 10: independent/hands-on corroboration of the embedded accounts flow, and resolution of the compliance/account-stability concerns raised by users.", "evidenceIds": [ "wise-docs-5", "wise-docs-1", "wise-docs-4", "wise-docs-11", "wise-comm-6", "wise-comm-5" ] }, { "productId": "wise", "storyId": "fast-cross-border-transfer", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Vendor docs explicitly claim most payments arrive in under 20 seconds and cover 40+ currencies/160+ countries, directly supporting the story. However, community evidence shows operational disruptions (account detail changes, account blocks) that undermine reliability of the payment experience, and there's no independent corroboration of actual speed claims. Missing for 10: independent/hands-on verification of the under-a-minute speed claim, and resolution of community reliability concerns.", "evidenceIds": [ "wise-docs-2", "wise-docs-7", "wise-docs-12", "wise-comm-3", "wise-comm-6" ] }, { "productId": "wise", "storyId": "fast-onboarding-switch", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains no claims or documentation about how long it takes a founder to open and fully activate a Wise Business account — no onboarding timeline, sign-up flow speed, or verification turnaround is mentioned. The only tangential items describe account creation breadth (160+ countries) and API payment docs, not onboarding speed, and community evidence instead highlights account blocks/changes (wise-comm-6, wise-comm-3) rather than fast onboarding.", "evidenceIds": [] }, { "productId": "wise", "storyId": "fdic-insurance-sweep", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Wise only documents passthrough FDIC insurance up to $250,000 through a single named Program Bank, not an automated multi-bank sweep network that would extend coverage beyond that cap; no evidence of sweeping deposits across multiple partner banks.", "evidenceIds": [ "wise-docs-11" ] }, { "productId": "wise", "storyId": "fee-free-foreign-card-spend", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Wise docs explicitly state cards can be issued worldwide and used to 'pay and withdraw cash worldwide without any hidden fees or markups,' directly matching the founder's story. Community evidence corroborates general reliability but doesn't specifically address card fee transparency, and there's no independent hands-on verification of the no-hidden-fee claim for card withdrawals abroad. Missing for 10: independent/hands-on confirmation of actual ATM withdrawal fees and card FX markup transparency in practice.", "evidenceIds": [ "wise-docs-4", "wise-docs-10", "wise-comm-4" ] }, { "productId": "wise", "storyId": "freeze-replace-card", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence shows Wise issues debit cards worldwide, but there is no mention of card freezing/locking or replacement-ordering functionality anywhere in the pack.", "evidenceIds": [ "wise-docs-4" ] }, { "productId": "wise", "storyId": "gl-sync-erp", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows Wise Business offers payment/API capabilities but nothing about ERP sync, journal entries, or accounting-integration connectors (e.g., QuickBooks/Xero/NetSuite bidirectional sync). No mention of any ERP integration exists in the pack.", "evidenceIds": [] }, { "productId": "wise", "storyId": "high-yield-savings-subaccount", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of a high-yield savings sub-account or automated transfer/sweep rules in Wise Business; evidence covers multi-currency accounts, payments, cards, and FDIC pass-through insurance only, not yield-generating savings or automation rules.", "evidenceIds": [] }, { "productId": "wise", "storyId": "instant-virtual-card-issuance", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence only mentions issuing debit cards worldwide (wise-docs-4) with no mention of virtual cards, spend controls, or scoping cards to a vendor/purpose — the specific capability finance leads need for scoped spend controls is absent.", "evidenceIds": [ "wise-docs-4" ] }, { "productId": "wise", "storyId": "invoice-creation-collection", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence covers receiving/sending money, multi-currency accounts, cards, and API payments, but nothing addresses creating or sending branded invoices with payment collection features.", "evidenceIds": [] }, { "productId": "wise", "storyId": "lock-exchange-rate", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Wise explicitly offers a rate lock ('Lock in exactly what your recipient will get for up to 24 hours') via wise-docs-8, directly matching the story, but this is a fixed 24-hour window rather than a flexible/finance-lead-configurable window, and there's no independent corroboration or API-level documentation of this feature for Business specifically. missing for 10: evidence of business-specific (vs. consumer) rate-lock terms, longer/configurable lock windows, and independent confirmation of reliability.", "evidenceIds": [ "wise-docs-8" ] }, { "productId": "wise", "storyId": "multi-currency-account-creation", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Wise Business documentation clearly supports holding and receiving in 40+ currencies with global account details from one account, matching the founder story directly. Missing for 10: independent hands-on review of the multi-currency dashboard/balance management UI itself (community evidence cited relates to account-detail change notices, not to the core multi-currency holding capability).", "evidenceIds": [ "wise-docs-3", "wise-docs-9", "wise-docs-12", "wise-docs-1" ] }, { "productId": "wise", "storyId": "multi-currency-interest", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence in the pack mentions interest-earning on multi-currency balances; only FDIC insurance passthrough and payment/transfer features are documented.", "evidenceIds": [] }, { "productId": "wise", "storyId": "multiple-checking-subaccounts", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack shows Wise Business supports multi-currency accounts, global payments, and cards, but nothing about creating multiple checking sub-accounts or auto-allocating incoming deposits across them—no rules-based deposit splitting or sub-account structuring is mentioned anywhere.", "evidenceIds": [] }, { "productId": "wise", "storyId": "no-fee-card-cashback", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack of a cashback or rewards program for card spend; the evidence covers currency accounts, payments, and card issuance only.", "evidenceIds": [] }, { "productId": "wise", "storyId": "one-click-payment-approval", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items mention approval workflows, permission roles, or multi-user authorization for payments in Wise Business; all evidence covers account setup, transfers, and unrelated account-detail issues.", "evidenceIds": [] }, { "productId": "wise", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Docs show the API can create accounts, send/receive payments, and issue cards, mirroring several core UI capabilities (wise-docs-1..6), but there's no evidence of full parity — no OpenAPI/spec found (wise-probe-2 all 404), and UI-only features like rate locks, FDIC opt-in, or dispute/support workflows aren't shown as API-accessible. missing for 10: a published complete API reference/OpenAPI spec, explicit parity statement, coverage of rate-lock/insurance/account-management UI features via API, and independent confirmation of full functional overlap.", "evidenceIds": [ "wise-docs-1", "wise-docs-2", "wise-docs-3", "wise-docs-4", "wise-docs-6", "wise-probe-2" ] }, { "productId": "wise", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of any data export/portability feature (transaction history, statements in open formats like CSV/JSON) or account-closure data-export process; evidence pack only covers payment features and API docs, with no mention of exporting or leaving with your data.", "evidenceIds": [] }, { "productId": "wise", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a closed-source fintech SaaS product, not a software project expected to publish source code under an open license; this axis is a category error for this product type.", "evidenceIds": [] }, { "productId": "wise", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a regulated fintech SaaS platform for cross-border payments; self-hosting a licensed financial/banking service is a category error, not a plausible axis for this kind of product.", "evidenceIds": [] }, { "productId": "wise", "storyId": "physical-card-issuance", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Evidence only shows a thin claim that Wise lets businesses 'issue debit cards worldwide' with no detail on assigning employee roles, spending controls, or credit card issuance. missing for 10: evidence of credit card issuance, role-based permissions/spend controls per employee, and any independent corroboration of card issuance workflow.", "evidenceIds": [ "wise-docs-4" ] }, { "productId": "wise", "storyId": "po-matched-invoice-automation", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a money-transfer/business-account platform; PO matching, invoice coding, and payment-routing/approval workflows are AP-automation category features entirely outside its scope, not something in evidence to fail at.", "evidenceIds": [] }, { "productId": "wise", "storyId": "privacy-data-residency", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/banking product, not a data-storage or AI-infrastructure platform; data residency/region selection is not a feature category it addresses. This is a category mismatch (wrong axis) rather than a missing capability.", "evidenceIds": [] }, { "productId": "wise", "storyId": "privacy-no-training", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a payments/fintech product; AI training data opt-out is not a relevant axis for this category of product, and no evidence pack items relate to AI model training data usage.", "evidenceIds": [] }, { "productId": "wise", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses data retention policies, deletion controls, or privacy/data-lifecycle management for Wise Business; all evidence covers payments, account features, and unrelated account-closure incidents.", "evidenceIds": [] }, { "productId": "wise", "storyId": "privacy-telemetry-optout", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Wise Business is a fintech/payments platform, not an AI agent or developer tool with telemetry collection concerns; telemetry opt-out is not a relevant axis for this product category.", "evidenceIds": [] }, { "productId": "wise", "storyId": "receipt-matching-by-email-upload", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack items mention receipt capture, receipt attachment, email-in receipts, or expense/spend management matching features for Wise Business; evidence covers payments, accounts, cards issuance, and unrelated community complaints about account detail changes.", "evidenceIds": [] }, { "productId": "wise", "storyId": "receive-multi-currency", "verdict": "disputed", "quality": 5, "confidence": "medium", "rationale": "Wise Business documents receiving payments via local account details in 40+ currencies/160+ countries (wise-docs-1,3,9,12), but concrete hands-on reports show these account details can change with zero notice, breaking real business payment flows with enterprise clients on NET30/90 terms (wise-comm-3, wise-comm-5), and one founder's entire business account was blocked due to a category mismatch (wise-comm-6). Missing for 10: independent verification of stability of account details over time, and resolution/track record after the reported incidents.", "evidenceIds": [ "wise-docs-1", "wise-docs-3", "wise-docs-9", "wise-docs-12", "wise-comm-3", "wise-comm-5", "wise-comm-6" ] }, { "productId": "wise", "storyId": "request-limit-increase", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of a self-service screen or workflow for requesting transaction limit increases; evidence covers account creation, payments, cards issuance, and unrelated community complaints about account detail changes and profile mismatches.", "evidenceIds": [] }, { "productId": "wise", "storyId": "role-based-permissions", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack addresses role-based access control, permissions granularity, or team/location/department-level management; all evidence covers payments, currency accounts, and unrelated account-closure incidents.", "evidenceIds": [] }, { "productId": "wise", "storyId": "send-domestic-ach-wire", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Wise Business docs confirm global/business payments via API and US bank account details (implying domestic transfers), but no explicit mention of ACH or wire transfer mechanics, batch vendor payments, or approval workflows for finance teams. Community reports also show real friction — sudden change of US account/routing details with no notice (wise-comm-3) and a business account being fully blocked over a category mismatch (wise-comm-6) — which undercuts reliability for ongoing vendor payments. missing for 10: explicit ACH/wire terminology, vendor batch-payment/approval workflow evidence, and confirmation that account-detail volatility doesn't disrupt recurring vendor payments.", "evidenceIds": [ "wise-docs-2", "wise-docs-6", "wise-docs-12", "wise-comm-3", "wise-comm-6" ] }, { "productId": "wise", "storyId": "send-international-payments", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Docs show international payments in 40+ currencies with rate lock guarantees and no hidden fees/markups, directly matching the finance-lead's need for transparent-fee international payments; community evidence corroborates it's used for real business payments (NET 30-90 terms) and is seen as reliable vs alternatives. Missing for 10: independent fee-transparency audits and more detail on actual fee schedules beyond marketing claims, plus account-detail-change incidents that add operational friction risk not solely about fee transparency.", "evidenceIds": [ "wise-docs-2", "wise-docs-7", "wise-docs-8", "wise-docs-10", "wise-docs-12", "wise-comm-4", "wise-comm-5" ] }, { "productId": "wise", "storyId": "transfer-delivery-estimate", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Wise advertises general speed ('most arrive in under 20 seconds') and a rate-lock guarantee, but there is no evidence of a specific, itemized delivery-time estimate shown per ACH/wire transfer before confirmation. missing for 10: concrete UI/API evidence of a per-transaction delivery estimate for ACH/wire, confirmation-screen screenshots or docs showing exact ETA, independent corroboration of estimate accuracy.", "evidenceIds": [ "wise-docs-7", "wise-docs-8" ] }, { "productId": "wise", "storyId": "universal-transaction-search", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of a universal search bar across transactions, vendors, and cards, nor any UI navigation feature that lets a finance-lead jump from search results into initiating a payment. Evidence pack only covers payment sending, currency accounts, cards issuance, and unrelated account-closure complaints.", "evidenceIds": [] } ]