Ramp vs Navan

Accounting sync

1. finance leadTransactions sync to QuickBooks, NetSuite, or Xero with GL account, class, and department mappings I control

   weight 3 · round to Ramp
   Ramp~partialclaimed6/10

   Ramp documents native QuickBooks, NetSuite, and Xero integrations with transaction sync, GL account coding, and reconciliation/matching tools (ramp-docs-25, ramp-docs-26, ramp-docs-27, ramp-docs-28, ramp-docs-32), plus multi-entity sync (ramp-docs-24). However, none of the evidence explicitly describes finance-lead control over class or department dimension mappings, only general GL account coding and reconciliation. Missing for 10: explicit documentation of class/department mapping configuration and user control over those field mappings during sync.

   • [claimed-docs] “Sync your transaction and reimbursement data to multiple entities in a single step, for less work.”
   • [claimed-docs] “Eliminate manual verification with Ramp's 3-way matching of purchase orders, receipts, and invoices”
   • [claimed-docs] “Gain confidence in your numbers with Ramp's built-in reconciliation tool that verifies balances between both platforms”
   • [claimed-docs] “Process vendor bills from start to finish: initiate your process in either NetSuite or Ramp, and complete it with Ramp payments”
   • [claimed-docs] “initiate your process in either Xero or Ramp and complete it with Ramp payments”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan—none0/10

   The evidence pack contains no mention of QuickBooks, NetSuite, Xero, or any accounting-system sync, nor GL account/class/department mapping controls — it only covers Navan's API/MCP for expense querying, travel booking, and rewards. This is a plausible and expected axis for a T&E platform, but nothing in the evidence demonstrates it.

   ⚑ flag

Close

1. finance leadSpend is coded as it happens — merchant, category, memo, receipt — so month-end close is a review, not an archaeology dig

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp documents real-time receipt capture, auto-fill of merchant/category/memo at swipe, GL coding, and auto-approval within policy (ramp-docs-8, ramp-docs-32, ramp-docs-21), plus reconciliation/3-way matching tools for close (ramp-docs-25, ramp-docs-26). This directly matches the story of spend being coded at time-of-swipe rather than reconstructed later. Missing for 10: independent/hands-on verification of accuracy claims and no explicit end-to-end month-end close workflow walkthrough beyond marketing copy.

   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [claimed-docs] “Ramp gives you infinite teammates who work around the clock—flagging fraud, coding expenses, and enforcing policy.”
   • [claimed-docs] “Eliminate manual verification with Ramp's 3-way matching of purchase orders, receipts, and invoices”
   • [claimed-docs] “Gain confidence in your numbers with Ramp's built-in reconciliation tool that verifies balances between both platforms”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”

   proof ↗⚑ flag

   Navan~partialclaimed7/10

   Navan's card-transaction API, receipt scanning, custom-field management, and policy-violation flagging (navan-docs-4, -21, -22, -23, -24) show spend arriving already tagged by merchant/category/policy status, and MCP queries let a finance lead pull flagged/over-limit items by department in natural language (navan-docs-5, -21) instead of manually reconciling. Missing for 10: explicit evidence of automatic memo generation and confirmation that coding happens in real time at swipe rather than batch/after-the-fact, plus independent (non-vendor) validation of close-time accuracy.

   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”

   proof ↗⚑ flag

Multi entity

1. finance leadRun multiple legal entities and currencies in one account with consolidated reporting and per-entity books

   weight 2 · round to Ramp
   Ramp~partialclaimed5/10

   Ramp has a dedicated multi-entity page indicating it can sync transactions and reimbursement data across multiple entities in one step, and reimbursements support 70+ countries/40 currencies, suggesting multi-entity/multi-currency support. However, the evidence pack lacks detail on consolidated reporting dashboards or explicit per-entity books/chart-of-accounts separation. Missing for 10: explicit consolidated reporting evidence, per-entity ledger/books detail, multi-currency accounting (not just reimbursement) specifics.

   • [claimed-docs] “Sync your transaction and reimbursement data to multiple entities in a single step, for less work.”
   • [claimed-docs] “Reimburse employees with confidence in more than 70 countries and 40 currencies, knowing they can be paid in two days or less in their local…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence pack covers Navan's MCP/API for expense and travel data, card management, and pricing/rewards, but contains no mention of multi-entity or multi-currency account structures, consolidated reporting, or per-entity books — core requirements for finance-lead accounting-close workflows.

   ⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Ramp✓fullprobed9/10

   Ramp hosts a live, HTTP-200 llms.txt index (ramp-probe-1) plus a full suite of llms-guides/*.txt agent-oriented docs covering getting started, auth, webhooks, CLI, and MCP for AI agents (ramp-docs-1 through ramp-docs-6), directly matching the story of pointing an agent at machine-readable docs. Missing for 10: independent third-party confirmation that agents actually consume/parse this index successfully in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”
   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”

   proof ↗⚑ flag

   Navan✓fullprobed9/10

   A live llms.txt file is confirmed at developer.navan.com/llms.txt (HTTP 200) describing MCP-based agent access, and the developer portal has dedicated agent-oriented docs (/mcp/, /api/) with example natural-language queries. Missing for 10: independent third-party confirmation that agents successfully consume this llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.navan.com/llms.txt # Navan Developer Portal > Connect AI assistants to Navan travel and expen…”
   • [claimed-docs] “Connect AI assistants — Claude, Cursor, ChatGPT, Codex, OpenClaw — to Navan data using the Model Context Protocol.”
   • [claimed-docs] “The Navan MCP lets you connect Navan to your favorite AI products, so you can query Navan spend and travel data using natural language.”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Ramp
   Ramp~partialprobed6/10

   Ramp exposes a public API (OAuth token auth) and an official CLI that can be scripted 'from your terminal or AI agent' (ramp-docs-1, ramp-docs-2, ramp-docs-4, ramp-probe-3), which supports headless/automated use, and webhooks enable event-driven automation (ramp-docs-3). However, there is no explicit documentation of running Ramp in a CI pipeline, no CI/CD examples, and no mention of non-interactive auth flows suited for CI (e.g., service accounts) — missing for 10: explicit CI/CD usage examples, headless auth flow documentation for automated pipelines, independent confirmation of CLI use in CI.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”
   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan~partialclaimed5/10

   Navan's API documents an OAuth 2.0 client-credentials flow (machine-to-machine auth with no interactive login), which is the kind of mechanism needed to call Navan programmatically from a CI/automation pipeline, and its REST/webhook endpoints could be scripted headlessly. However, there is no explicit CI documentation, CLI, or example of running Navan (or its MCP server) unattended in a pipeline — missing for 10: explicit CI/automation guide, headless MCP server deployment instructions, and any hands-on evidence of it being run in CI.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”

   proof ↗⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Ramp
   Ramp✓fullprobed9/10

   Ramp documents an official MCP server ('Ramp MCP') letting users connect AI assistants like ChatGPT and Claude to query data and take actions, with a dedicated support article and docs page confirming it exists and works (e.g., locking a card, finding missing receipts). This is corroborated by both first-party docs and a support-article walkthrough with concrete example prompts. Missing for 10: independent third-party (non-Ramp) hands-on review of the MCP server's reliability.

   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan✓fullprobed8/10

   Navan publishes an official MCP server (developer.navan.com/mcp/) explicitly for connecting AI assistants like Claude, Cursor, ChatGPT to Navan spend/travel data, with documented natural-language query examples and OAuth-secured API endpoints backing it. Missing for 10: independent/hands-on third-party corroboration of the MCP server working in practice beyond vendor docs.

   • [claimed-docs] “Connect AI assistants — Claude, Cursor, ChatGPT, Codex, OpenClaw — to Navan data using the Model Context Protocol.”
   • [claimed-docs] “The Navan MCP lets you connect Navan to your favorite AI products, so you can query Navan spend and travel data using natural language.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.navan.com/llms.txt # Navan Developer Portal > Connect AI assistants to Navan travel and expen…”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Ramp
   Ramp✓fullprobed8/10

   Ramp documents an official CLI (docs.ramp.com/llms-guides/cli.txt and github.com/ramp-public/ramp-cli) explicitly designed for AI-native use, allowing OAuth authentication, expense management, bill approval, and travel booking 'from your terminal or AI agent,' and positions it alongside MCP for agentic workflows. Missing for 10: independent/hands-on verification of CLI usage and more detail on command coverage/maturity beyond first-party docs.

   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to Ramp
   Ramp✓fullprobed9/10

   Ramp documents a public REST API (Transactions, OAuth 2.0 authorization, webhooks) with a machine-readable llms.txt index, plus a CLI and MCP server explicitly built for driving Ramp actions programmatically or via AI agents. This covers documented public API access comprehensively across auth, data retrieval, and actions. Missing for 10: independent third-party developer reports/hands-on confirmation of API robustness beyond Ramp's own docs.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan✓fullprobed8/10

   Navan provides a documented public API (developer.navan.com) with OAuth 2.0 client-credentials auth, retrieval/update endpoints across expense, card, payroll, custom fields, and webhooks, plus a first-party MCP server for natural-language AI access — corroborated by a live llms.txt probe. Missing for 10: independent third-party developer accounts of building against the API and clearer rate-limit/versioning documentation.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.navan.com/llms.txt # Navan Developer Portal > Connect AI assistants to Navan travel and expen…”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”
   • [claimed-docs] “Connect AI assistants — Claude, Cursor, ChatGPT, Codex, OpenClaw — to Navan data using the Model Context Protocol.”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Ramp
   Ramp✓fullprobed8/10

   Ramp's OAuth 2.0 implementation provides granular scoped permissions for API access (ramp-docs-2), and dedicated Agent Cards plus MCP/CLI docs show explicit support for issuing scoped credentials/action authority to AI agents specifically (ramp-docs-6, ramp-docs-7, ramp-docs-5). This directly matches the least-privilege-for-agents story. Missing for 10: independent/hands-on verification of scope granularity in practice and explicit documentation of per-agent credential revocation/audit trails.

   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan~partialprobed3/10

   Navan's developer docs mention an OAuth 2.0 client-credentials flow for API access (navan-docs-2), which implies some credential-based authentication, but there is no explicit documentation of scoped permissions, granular access levels, or least-privilege controls specifically for AI agents connecting via MCP or API. missing for 10: explicit scope/permission definitions, least-privilege role configuration, agent-specific credential restrictions, and any documentation or independent verification of access-control granularity.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Connect AI assistants — Claude, Cursor, ChatGPT, Codex, OpenClaw — to Navan data using the Model Context Protocol.”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Navan
   Ramp—none0/10

   Evidence shows Ramp offers a REST API, OAuth, webhooks, a CLI, and an MCP server, but nowhere mentions official client SDKs (e.g., Python, JS, Go libraries) for building against Ramp's API. Missing for 10: any documentation of official SDKs/client libraries in specific languages, package registry listings, or SDK-specific quickstart guides.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan~partialprobed5/10

   Navan documents an official REST API (OAuth2 client-credentials, expense/card/travel endpoints, webhooks) and an MCP server for AI assistants, which developers can build against, but there is no evidence of language-specific official SDKs (e.g., Python/JS client libraries) — only raw API/MCP documentation. missing for 10: explicit SDK packages/libraries, code samples in multiple languages, independent developer corroboration of SDK usage.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.navan.com/llms.txt # Navan Developer Portal > Connect AI assistants to Navan travel and expen…”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp docs explicitly describe webhooks for real-time event notifications from a Ramp account, directly matching the story. Missing for 10: no details on event types/payload schema, delivery guarantees, or independent/hands-on verification of webhook reliability.

   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”

   proof ↗⚑ flag

   Navan—none0/10

   Webhooks are mentioned only once in passing as part of the API surface (navan-docs-2), with no documentation of subscription mechanics, event types, payload formats, or delivery guarantees; nothing shows an AI-native user can actually subscribe to events via webhooks.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Navan
   Ramp✓fullprobed7/10

   Ramp Intelligence and related features surface AI-generated recommendations (recommended actions on spend requests, auto-coding of expenses, fraud flagging, contract parsing) directly inside the product, and Ramp MCP lets users query data and get AI-driven suggestions like drafting reminders for missing receipts. missing for 10: independent/hands-on validation of insight quality and a fuller first-party doc detailing the breadth of proactive insights beyond the marketing snippets and MCP examples.

   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “Ramp gives you infinite teammates who work around the clock—flagging fraud, coding expenses, and enforcing policy.”
   • [claimed-docs] “Drop in a contract or screenshot and Ramp's AI parses details and auto-fills the request form”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan✓fullclaimed8/10

   Navan's Ava AI and MCP integration provide AI-generated insights such as analyzing travel/spend data, summarizing by category, comparing to policy, predicting future spend, and flagging policy violations, all directly from Navan data. missing for 10: independent/hands-on verification of insight quality beyond vendor blog and docs, and details on how proactive/unprompted these suggestions are versus query-driven.

   • [claimed-docs] “Analyze travel spend and craft suggestions to save”
   • [claimed-docs] “Summarize travel spend by month and by category”
   • [claimed-docs] “Analyze travel spend and compare it to company policy”
   • [claimed-docs] “Predict future travel spend habits with ease”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Ramp
   Ramp~partialprobed5/10

   Ramp offers webhooks, an API, MCP server, and CLI that agents can use to take actions like locking cards or drafting reminders, which supports agentic workflows, but these are largely triggered interactions rather than documented autonomous/scheduled background automations that run without a prompting event. Rules-based workflows (e.g., procurement routing, policy enforcement) run automatically but are conditional business rules, not general-purpose autonomous agent automations. missing for 10: explicit support for scheduled/recurring autonomous agent runs, evidence of persistent background agent execution without user-initiated trigger, and independent confirmation of such autonomous operation.

   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [claimed-docs] “Rules-based workflows route requests to the right stakeholders automatically based on vendor type, spend category, or dollar amount”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence shows Navan's AI features (MCP, Ava) are query/chat-based tools that answer questions or analyze spend on request, and Navan Edge explicitly states it 'will always ask for your explicit confirmation before booking, changing, or canceling any trip,' which is the opposite of autonomous background automation. No workflow, trigger, or scheduling mechanism for unattended background automations is documented anywhere in the pack.

   • [claimed-docs] “Navan Edge will always ask for your explicit confirmation before booking, changing, or canceling any trip.”
   • [claimed-docs] “No. Navan Edge will always ask for your explicit confirmation before booking, changing, or canceling any trip.”
   • [claimed-docs] “The Navan MCP lets you connect Navan to your favorite AI products, so you can query Navan spend and travel data using natural language.”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Unlimited policy and approval workflows”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Navan
   Ramp~partialprobed5/10

   Ramp offers agentic automation ('infinite teammates' handling fraud flagging, coding, policy enforcement) and lets users delegate tasks via natural language through its MCP integration (e.g., 'Find transactions with missing receipts...', 'Lock my card'), but these delegated-task examples run through external AI assistants (ChatGPT, Claude) connected via MCP rather than a native, built-in conversational assistant inside the Ramp product itself. Missing for 10: evidence of an in-app chat/assistant UI natively embedded in Ramp (not via MCP to third-party LLMs), and independent confirmation of task delegation working end-to-end within the product.

   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Ramp gives you infinite teammates who work around the clock—flagging fraud, coding expenses, and enforcing policy.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan✓fullclaimed7/10

   Navan documents built-in AI assistants (Ava for analyzing/summarizing/predicting travel spend, and Navan Edge for booking/changing/canceling trips with confirmation) that users can delegate expense and travel tasks to. Missing for 10: independent/hands-on verification of these assistants in action and detail on broader task types beyond travel/expense.

   • [claimed-docs] “Analyze travel spend and craft suggestions to save”
   • [claimed-docs] “Summarize travel spend by month and by category”
   • [claimed-docs] “Analyze travel spend and compare it to company policy”
   • [claimed-docs] “Predict future travel spend habits with ease”
   • [claimed-docs] “Navan Edge provides 24/7 access to human travel agents via chat or phone at +1-877-536-3343 in English.”
   • [claimed-docs] “Navan Edge will always ask for your explicit confirmation before booking, changing, or canceling any trip.”
   • [claimed-docs] “Navan Edge personalizes results based on: Your preferences shared during chat, Your booking history, Loyalty programs connected to your acco…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Ramp
   Ramp✓fullprobed8/10

   Ramp ships an official MCP server and CLI explicitly designed for natural-language operation ("query Ramp data and take actions with natural language"), with documented examples like locking a card or drafting reminder messages via plain-English commands, plus a CLI usable directly by AI agents. Missing for 10: independent/hands-on validation beyond vendor docs and no broad third-party confirmation of reliability across all agentic actions.

   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan✓fullprobed7/10

   Navan's MCP server and Ava assistant let users query spend, travel, policy, and card data with natural-language commands (e.g. flagged expenses, rideshare policy violations), and Navan Edge/Ava support conversational trip booking with confirmation steps. missing for 10: independent/hands-on verification of natural-language accuracy and breadth beyond vendor docs, and no evidence of NL commands for arbitrary in-app actions beyond travel/expense domains.

   • [claimed-docs] “Connect AI assistants — Claude, Cursor, ChatGPT, Codex, OpenClaw — to Navan data using the Model Context Protocol.”
   • [claimed-docs] “The Navan MCP lets you connect Navan to your favorite AI products, so you can query Navan spend and travel data using natural language.”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Analyze travel spend and craft suggestions to save”
   • [claimed-docs] “Navan Edge will always ask for your explicit confirmation before booking, changing, or canceling any trip.”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Ramp—none0/10

   Evidence shows Ramp has API docs, OAuth guides, webhooks, and a machine-readable llms.txt index, but nothing describes an interactive API reference with runnable/live code examples (e.g., a Swagger/Postman-style explorer). Missing for 10: any mention of an interactive console or runnable example feature in the docs.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence shows a developer portal describing API endpoints (OAuth, expense/card endpoints, webhooks) and an MCP server for natural-language queries, but nothing indicates an interactive API reference with runnable/try-it-now code examples (e.g., Swagger/OpenAPI explorer or live sandbox).

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to Ramp
   Ramp~partialprobed3/10

   Ramp exposes a machine-readable llms.txt index for its Developer API docs, which is AI-native friendly, but there's no evidence of an actual OpenAPI/Swagger spec file being published or downloadable. Missing for 10: an explicit OpenAPI/Swagger spec document, a documented download endpoint, or third-party confirmation that the API schema is available in a standard machine-readable spec format.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”
   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”

   proof ↗⚑ flag

   Navan—none0/10

   Navan's developer docs describe REST API endpoints, OAuth 2.0 flows, and an MCP server, but no evidence pack item mentions a downloadable OpenAPI/Swagger spec or any machine-readable API definition file. missing for 10: explicit OpenAPI/Swagger spec file, API reference generated from a spec, or a documented download link.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Ramp—none0/10

   No evidence of a sandbox/test environment for Ramp's API, CLI, or MCP integrations; all docs reference live transactions, cards, and production data flows. Missing for 10: any mention of a sandbox/test mode, test API keys, or non-production environment for developers/AI agents.

   ⚑ flag

   Navan—none0/10

   No evidence pack item mentions a sandbox, staging, or test environment for Navan's API, MCP server, or app; all endpoints and integrations described operate on live/production expense, travel, and card data. Missing for 10: any mention of a sandbox/test mode, staging API keys, or demo data environment separate from production.

   ⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Ramp—none0/10

   Evidence shows Ramp has an API, OAuth, webhooks, CLI, and MCP server, but nothing in the pack documents API versioning practices or a formal deprecation policy. missing for 10: versioning scheme documentation, deprecation policy/notice process, changelog or migration guidance for breaking changes.

   ⚑ flag

   Navan—none0/10

   The evidence pack documents Navan's API/MCP endpoints and OAuth flow but contains no mention of API versioning scheme or a documented deprecation policy for consumers to rely on.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”

   proof ↗⚑ flag

Ai coding

1. ai-native userAI codes and audits expenses for me — reading receipts, suggesting categories and memos, and catching duplicates or fraud

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp's docs show automatic receipt capture with AI-filled memos/categories (ramp-docs-8, ramp-docs-32), OCR line-item accuracy (ramp-docs-16), fraud flagging and expense coding via 'infinite teammates' AI (ramp-docs-21), duplicate/missing-item detection via MCP prompts (ramp-docs-29), and policy/match-based auditing (ramp-docs-17, ramp-docs-25, ramp-docs-9). This covers reading receipts, categorization/memo suggestion, and fraud/duplicate catching across first-party marketing and support docs. Missing for 10: independent/hands-on verification of accuracy claims and explicit named 'duplicate detection' feature documentation beyond marketing copy.

   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “Ramp's OCR captures each detail and line item with 99% accuracy.”
   • [claimed-docs] “Ramp checks every line item with two and three-way matching, so you know if something's off before sending.”
   • [claimed-docs] “Ramp gives you infinite teammates who work around the clock—flagging fraud, coding expenses, and enforcing policy.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”

   proof ↗⚑ flag

   Navan~partialprobed6/10

   Navan's MCP/API and Ava AI assistant let AI query flagged expenses, analyze spend, and check policy violations (navan-docs-5, navan-docs-6, navan-docs-22), plus native receipt scanning (navan-docs-24) — covering audit/flagging aspects. However there's no explicit evidence of AI auto-suggesting categories/memos or specifically detecting duplicate/fraudulent transactions. Missing for 10: automated category/memo suggestion, explicit duplicate-detection or fraud-catching functionality, and independent verification of these AI audit claims.

   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

Ai policy

1. ai-native userAn AI assistant enforces policy conversationally — chasing missing receipts, explaining declines, and answering "can I expense this?" before the spend happens

   weight 2 · round to Ramp
   Ramp✓fullprobed7/10

   Ramp's MCP/AI assistant explicitly chases missing receipts with drafted reminders (ramp-docs-29, ramp-docs-13), and policy enforcement happens conversationally with recommended actions and pre-spend policy visibility (ramp-docs-9, ramp-docs-10, ramp-docs-18). This covers the core of the story, though 'explaining declines' and answering 'can I expense this?' pre-spend are only indirectly evidenced via policy-status/recommended-action features rather than a direct conversational decline-explanation example. Missing for 10: independent/hands-on confirmation of the assistant explaining a specific decline conversationally, and an explicit pre-spend Q&A example beyond travel-booking policy status.

   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Let Ramp send reminders for missing items or request repayments for you.”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “See policy status for every option. No digging through static policy PDFs or wondering if trips will get rejected.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan~partialclaimed5/10

   The Navan MCP explicitly supports conversational policy Q&A — asking about policy, approval flows, and why a transaction was flagged/declined (navan-docs-22, navan-docs-6) — and Ava can compare travel spend to policy after the fact (navan-docs-19). However there is no evidence of proactive 'chasing missing receipts' workflows or a pre-spend 'can I expense this?' check before the transaction occurs; the examples shown are retrospective queries on past transactions/spend. Missing for 10: proactive missing-receipt nudges/reminders, and evidence of a pre-purchase 'is this expensable' conversational check.

   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”
   • [claimed-docs] “Analyze travel spend and compare it to company policy”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round drawn
   Ramp~partialclaimed4/10

   Ramp's API/MCP/CLI let users query and act on data programmatically (e.g., finding all transactions missing receipts across the last 14 days) and sync data to multiple entities in one step, suggesting some bulk-style automation. However, there is no explicit documentation of true bulk endpoints (e.g., batch update/create across many items) or bulk card issuance/approval workflows via API. Missing for 10: explicit bulk API endpoints, batch transaction/approval operations, and independent confirmation of bulk-scale automation.

   • [claimed-docs] “Sync your transaction and reimbursement data to multiple entities in a single step, for less work.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”

   proof ↗⚑ flag

   Navan~partialclaimed4/10

   The API docs mention batch-managing custom field option values and polling async job status, implying some bulk-processing capability, but there is no evidence of general bulk operations (e.g., bulk-approving multiple expenses, bulk-updating many transactions) across the platform for an AI-native user. missing for 10: evidence of bulk approve/reject workflows, bulk transaction updates via MCP, and independent confirmation that bulk API calls work at scale.

   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp supports webhooks for real-time event notifications, rules-based workflows that automatically route requests based on vendor/category/amount, spend limits and merchant blocking enforced pre-spend, automatic reminders/repayment requests, and auto-approval of in-policy transactions without manual filing — collectively demonstrating rule-driven automatic actions on events across its expense/procurement/card platform. Missing for 10: a documented general-purpose 'if-this-then-that' custom rule builder exposed to end users (vs. built-in policy categories) and independent/hands-on corroboration of these automation flows working as described.

   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “Create personalized workflows that only notify the right people, based on spend amount or team role, and keep visibility high.”
   • [claimed-docs] “Let Ramp send reminders for missing items or request repayments for you.”
   • [claimed-docs] “Rules-based workflows route requests to the right stakeholders automatically based on vendor type, spend category, or dollar amount”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan~partialclaimed4/10

   Navan documents configurable 'policy and approval workflows' and webhook endpoints, which imply some rule-based triggering of actions (e.g., flags, approvals) on expense events, but there is no explicit documentation of a user-facing rule/automation builder for defining custom event-triggered actions. Missing for 10: dedicated automation/rules engine documentation, examples of custom trigger-action definitions, and independent verification of automation depth beyond basic policy enforcement.

   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Ramp—none0/10

   Ramp's automation is event-driven (webhooks) or rules-based (route requests, reminders, auto-rebooking) rather than a documented recurring-job/scheduler capability that an AI agent could invoke via API, MCP, or CLI. No evidence of cron-like or interval-based scheduling for workflows.

   ⚑ flag

   Navan—none0/10

   Navan's evidence covers MCP-based querying, expense/travel management, webhooks, and async job polling, but there is no mention of scheduling recurring jobs, cron-like automation, or persistent workflow triggers for AI-native users. Absence of evidence for this applicable automation-depth capability yields none.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   Ramp—none0/10

   Ramp's evidence covers automating expense/spend workflows, MCP/CLI/API access, and policy enforcement, but there is no mention of versioning automations/workflows, reviewing changes, or rolling back to prior configurations. Rules-based workflows (docs-23) and permissioning are described but no version history, diff/audit trail, or rollback mechanism is documented.

   ⚑ flag

   Navan—none0/10

   No evidence of any versioning, review, or rollback mechanism for automations/workflows in Navan or its MCP/API offerings; the pack covers expense/travel management, MCP querying, and API endpoints but nothing about automation version control or rollback.

   ⚑ flag

Bill pay

1. finance leadRun accounts payable in the same platform — capture invoices, route approvals, and pay vendors by ACH, check, or wire

   weight 2 · round to Ramp
   Ramp~partialclaimed6/10

   Ramp's Bill Pay evidence shows invoice OCR capture (99% accuracy), 2/3-way matching, and rules-based approval routing (ramp-docs-16, ramp-docs-17, ramp-docs-23), plus 'complete it with Ramp payments' in NetSuite/Xero integrations (ramp-docs-27, ramp-docs-28) confirming payment execution within the platform. However, none of the evidence explicitly states support for ACH, check, or wire as distinct payment rails for vendor payments. Missing for 10: explicit documentation of ACH/check/wire payment method options, and independent/hands-on confirmation of the full AP workflow.

   • [claimed-docs] “Ramp's OCR captures each detail and line item with 99% accuracy.”
   • [claimed-docs] “Ramp checks every line item with two and three-way matching, so you know if something's off before sending.”
   • [claimed-docs] “Rules-based workflows route requests to the right stakeholders automatically based on vendor type, spend category, or dollar amount”
   • [claimed-docs] “Process vendor bills from start to finish: initiate your process in either NetSuite or Ramp, and complete it with Ramp payments”
   • [claimed-docs] “initiate your process in either Xero or Ramp and complete it with Ramp payments”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence covers Navan's travel and expense management (card transactions, reimbursements, receipts, policy approvals) but contains no mention of invoice capture, vendor bill management, or paying vendors via ACH, check, or wire — the core AP capabilities the story requires.

   ⚑ flag

Card controls

1. finance leadRestrict cards by category, merchant, and amount — and the platform auto-locks or declines out-of-policy spend at the point of sale

   weight 3 · round to Ramp
   Ramp✓fullclaimed8/10

   Docs explicitly describe issuing cards with attached controls, custom permissions per vendor/category/team, blocking risky merchants or categories before spend happens, and per-vendor spending limits on virtual cards — matching category/merchant/amount restriction and pre-spend enforcement. Missing for 10: independent/hands-on confirmation of real-time point-of-sale decline behavior and explicit 'auto-lock' mechanics beyond policy blocking language.

   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “A finance team issues instant virtual cards for each software subscription with per-vendor spending limits, giving real-time visibility into…”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence shows general card management (active/inactive status), policy workflows, and MCP queries about flagged/violating transactions, but nothing documents configurable restrictions by category, merchant, or amount, nor automatic point-of-sale locking/declining of out-of-policy spend. missing for 10: explicit documentation of category/merchant/amount-based card controls, missing for 10: evidence of real-time auto-lock or point-of-sale decline enforcement.

   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”
   • [claimed-docs] “Connect existing corporate or business credit cards”
   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”

   proof ↗⚑ flag

Card issuance

1. founderIssue physical and virtual corporate cards to the team in minutes, each with its own spend limit

   weight 3 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp docs explicitly describe issuing physical and virtual cards with per-card/per-vendor spend limits, permissions, and real-time visibility (ramp-docs-7, ramp-docs-11, ramp-docs-31), matching the founder story closely. Missing for 10: independent hands-on confirmation of the 'minutes' setup speed and explicit UI walkthrough evidence beyond marketing copy.

   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “A finance team issues instant virtual cards for each software subscription with per-vendor spending limits, giving real-time visibility into…”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence only shows querying/viewing existing card status via MCP (navan-docs-7) and connecting existing cards (navan-docs-9), but nothing about issuing new physical or virtual cards, setting per-card spend limits, or speed of issuance ('minutes'). Missing for 10: any documentation of card issuance workflow, virtual card creation, spend-limit configuration, or time-to-issue claims.

   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”
   • [claimed-docs] “Connect existing corporate or business credit cards”

   proof ↗⚑ flag

Virtual cards

1. finance leadCreate single-vendor virtual cards for SaaS subscriptions and procurement so one compromised vendor never exposes shared credit

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp documents creating custom/virtual cards with per-vendor spend limits explicitly for SaaS subscriptions, avoiding shared card numbers (ramp-docs-31, ramp-docs-11, ramp-docs-7), plus spend controls and merchant blocking (ramp-docs-9). missing for 10: independent/hands-on third-party corroboration beyond vendor marketing copy.

   • [claimed-docs] “A finance team issues instant virtual cards for each software subscription with per-vendor spending limits, giving real-time visibility into…”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”

   proof ↗⚑ flag

   Navan—none0/10

   The evidence pack covers Navan's MCP/API integrations, travel booking, rewards, and pricing highlights, but contains no mention of virtual card creation, single-vendor card controls, or SaaS/procurement card issuance. Card-related evidence only covers connecting existing corporate cards and viewing/managing card transaction data, not creating new single-vendor virtual cards.

   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”
   • [claimed-docs] “Connect existing corporate or business credit cards”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”

   proof ↗⚑ flag

Agent access

1. ai-native userAn agent can pull uncoded transactions via API or MCP, propose categorizations and policy flags, and push clean coding back for review

   weight 3 · round to Ramp
   Ramp~partialprobed6/10

   Ramp offers both API (Transactions API, OAuth) and MCP access, and MCP examples show pulling uncoded transactions (missing receipts/memos) and drafting messages, plus AI auto-coding of transactions to GL accounts. However, there's no explicit documented workflow showing an agent proposing categorizations/policy flags and pushing 'clean coding back for review' via MCP/API as a distinct human-review step. missing for 10: explicit end-to-end example of agent proposing coding+policy flags and submitting for human review via MCP/API, independent/hands-on confirmation of this workflow.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Ramp gives you infinite teammates who work around the clock—flagging fraud, coding expenses, and enforcing policy.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”

   proof ↗⚑ flag

   Navan~partialclaimed5/10

   The API exposes retrieval and update endpoints for card/Connect-card transactions and custom-field management (navan-docs-2, navan-docs-4, navan-docs-23), and MCP lets agents query uncoded/flagged transactions and policy violations in natural language (navan-docs-5, navan-docs-6, navan-docs-21, navan-docs-22). However, MCP is documented primarily as a query/analysis interface, not a write-back tool, and there is no explicit documentation of an agent proposing categorizations/policy flags and pushing clean coding back for human review as a workflow. Missing for 10: explicit MCP write/update support for coding transactions, a documented propose-then-review workflow, and independent confirmation of this end-to-end loop.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”

   proof ↗⚑ flag

Api access

1. developerPull transactions, expenses, and receipts through a documented REST API with OAuth and scoped tokens

   weight 3 · round drawn
   Ramp✓fullprobed8/10

   Ramp documents a Transactions API accessed via access tokens, and OAuth 2.0 with scopes and multiple authorization flows for API access, plus webhooks for event notifications, confirming a documented REST API with scoped OAuth tokens for transaction/expense data. missing for 10: no explicit mention of a dedicated receipts endpoint or independent third-party corroboration of API behavior beyond vendor docs.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”

   proof ↗⚑ flag

   Navan✓fullclaimed8/10

   Navan's developer portal documents a REST API with OAuth 2.0 client-credentials flow, and endpoints covering transactions, expenses, receipts, custom fields, and webhooks. Missing for 10: explicit mention of scoped/permissioned tokens (vs just client-credentials) and independent third-party corroboration of the API's documented behavior beyond vendor docs.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [claimed-docs] “Receipt scanning for on-the-go expenses”

   proof ↗⚑ flag

Card api

1. developerIssue and manage cards programmatically — create a card with a limit, lock it, update controls — via the public API

   weight 2 · round to Ramp
   Ramp~partialprobed3/10

   Ramp's marketing pages describe issuing virtual/physical cards with spend controls (ramp-docs-7, ramp-docs-11) and the MCP integration shows a 'lock my card' action (ramp-docs-30), suggesting the underlying platform supports card issuance/locking, but the developer docs index only explicitly names a Transactions API (ramp-docs-1) and the llms.txt probe doesn't surface a dedicated Cards API with create/lock/update-controls endpoints. Missing for 10: explicit public API reference/endpoints for card creation, locking, and limit/control updates, and any independent confirmation these are callable outside the MCP/CLI natural-language layer.

   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”

   proof ↗⚑ flag

   Navan—none0/10

   The API docs mention retrieving/updating card transactions and MCP tools let you view card status (active/inactive, count), but there is no evidence of creating a new card, setting a spending limit, locking a card, or updating card controls programmatically via the public API — missing for 10: card creation endpoint, limit-setting endpoint, lock/freeze endpoint, control-update endpoint documentation.

   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Ramp
   Ramp~partialprobed6/10

   Ramp exposes a broad public API, CLI, and MCP server covering many UI actions (transactions, cards, bill approval, travel booking, expense management) per ramp-docs-1,3,4,5,6,29,30, but no documentation explicitly claims full feature parity between API/CLI/MCP and the UI, and several UI-only workflows (e.g., detailed policy configuration, multi-entity setup, procurement OCR flows) are not shown as API-accessible. Missing for 10: an explicit parity statement or exhaustive endpoint list covering all UI functions, and independent confirmation that no UI-only gaps exist.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Authenticate with OAuth, manage expenses, approve bills, book travel, and more from your terminal or AI agent.”
   • [claimed-docs] “Ramp MCP allows you to securely connect Ramp with AI assistants like ChatGPT and Claude, so you can query Ramp data and take actions with na…”
   • [claimed-docs] “Give an AI agent read access, action authority, and (with approval) real purchasing power on Ramp — through MCP, the Ramp CLI, or both.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “Lock my card — I can't find it.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”
   • [probe] “official MCP server documented at https://support.ramp.com/hc/en-us/articles/45516494479891-Ramp-MCP”
   • [probe] “official CLI documented at https://github.com/ramp-public/ramp-cli”

   proof ↗⚑ flag

   Navan~partialprobed5/10

   Navan's API/MCP covers expense retrieval/update, transactions, custom fields, receipts, webhooks, and read-style spend/policy queries, but there is no evidence of API parity for travel booking, rewards, or other core UI workflows (e.g., booking trips, managing 'price to beat', Navan Edge concierge features) — those remain UI/chat-only per docs. missing for 10: API endpoints for travel booking/itinerary management, evidence of full UI-to-API parity beyond expense/finance domain, independent confirmation of completeness.

   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”
   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Discover company fields, batch-manage option values, and poll async job status.”
   • [claimed-docs] “Global travel inventory and exclusive rates”
   • [claimed-docs] “Navan Edge provides 24/7 access to human travel agents via chat or phone at +1-877-536-3343 in English.”
   • [probe] “official MCP server documented at https://developer.navan.com/mcp/”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Ramp
   Ramp~partialprobed3/10

   Ramp exposes a Transactions API and OAuth-based developer access that lets a user programmatically pull data, but there is no documented full-account data export/portability feature (e.g., a 'download all my data' or GDPR-style export in open formats). missing for 10: explicit full data export/takeout functionality, confirmation of open-format (CSV/JSON) bulk export, evidence of exporting all data types (bills, cards, reimbursements) not just transactions.

   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”
   • [claimed-docs] “Ramp uses OAuth 2.0 for secure API access, providing granular permission control through scopes and supporting multiple authorization flows …”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.ramp.com/llms.txt # Ramp Developer API Machine-readable index for Ramp's Developer API documentati…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence shows API/MCP access for querying and updating expense/travel data, but nothing about bulk data export in open/portable formats or any documented account-closure/data-portability process for leaving the platform. Missing for 10: bulk export functionality, open-format data dumps, documented data portability/exit process.

   ⚑ flag

Approvals

1. finance leadBuild multi-step approval chains — manager, budget owner, finance — with delegation and escalation when approvers sit on requests

   weight 2 · round to Ramp
   Ramp~partialclaimed4/10

   Ramp's docs show rule-based approval routing to stakeholders based on vendor/category/amount and role-based notification workflows, plus policy-grounded recommended approve/reject actions, which supports building structured approval chains. However, there is no evidence of explicit multi-step manager→budget-owner→finance sequencing, delegation of approval authority, or escalation logic when an approver doesn't act. missing for 10: explicit delegation feature, escalation/timeout rules, and multi-tier approval chain configuration details.

   • [claimed-docs] “Rules-based workflows route requests to the right stakeholders automatically based on vendor type, spend category, or dollar amount”
   • [claimed-docs] “Create personalized workflows that only notify the right people, based on spend amount or team role, and keep visibility high.”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”

   proof ↗⚑ flag

   Navan~partialclaimed2/10

   Navan mentions 'Unlimited policy and approval workflows' as a pricing feature and MCP queries reference 'who needs to approve' a transaction, confirming approval workflows exist, but there is no evidence describing configurable multi-step chains (manager → budget owner → finance), delegation, or escalation logic when approvers sit idle. missing for 10: documentation of multi-step approval chain configuration, delegation rules, escalation timers/triggers, and named approver roles.

   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”

   proof ↗⚑ flag

Audit trail

1. finance leadEvery expense carries a full audit trail — edits, approvals, policy checks — that survives an external audit

   weight 2 · round drawn
   Ramp~partialclaimed4/10

   Ramp's docs show policy enforcement (submission requirements, spend limits, policy status checks) and approval workflows with recommended actions, plus reconciliation/3-way matching tools that touch on audit-adjacent controls (ramp-docs-9, ramp-docs-10, ramp-docs-17, ramp-docs-26). However, there is no explicit documentation of an immutable audit log, edit history tracking, or export/report designed specifically to survive an external audit review. Missing for 10: explicit audit-trail/edit-history logging feature, statement on audit log immutability or retention, and third-party/independent evidence of audit compliance (e.g., SOC2 audit trail usage).

   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “Ramp checks every line item with two and three-way matching, so you know if something's off before sending.”
   • [claimed-docs] “Gain confidence in your numbers with Ramp's built-in reconciliation tool that verifies balances between both platforms”
   • [claimed-docs] “Create personalized workflows that only notify the right people, based on spend amount or team role, and keep visibility high.”

   proof ↗⚑ flag

   Navan~partialclaimed4/10

   Navan documents policy/approval workflows and the ability to query why a transaction was flagged or who must approve it, which implies some traceability, but there is no explicit documentation of an immutable audit log, edit history, or audit-survivability guarantees. Missing for 10: explicit audit-trail/version-history documentation, evidence of edit logging, and any mention of external-audit compliance or SOC/ISO controls.

   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

Policy engine

1. finance leadCodify our expense policy — limits by category, role, and context — so in-policy expenses auto-approve and only exceptions reach a human

   weight 3 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp docs describe configurable spend limits by category/role/context, submission requirements, and blocking risky merchants/categories before spend happens (ramp-docs-9), plus in-policy auto-approval with GL coding and no expense report needed (ramp-docs-32), and recommended approve/reject actions grounded in policy for exceptions (ramp-docs-10). Custom card permissions and role/team-based notification routing further support codifying policy by role and context (ramp-docs-11, ramp-docs-12). Missing for 10: independent/hands-on verification of policy engine granularity and confirmation that auto-approval works reliably at scale beyond marketing copy.

   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “Create personalized workflows that only notify the right people, based on spend amount or team role, and keep visibility high.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan~partialclaimed5/10

   Navan advertises "unlimited policy and approval workflows" and its MCP/AI layer can explain which policy applies, why a transaction was flagged, and who must approve it, implying a rules engine with per-transaction policy limits (e.g., rideshare, hotel price caps). However, the evidence never explicitly describes configuring limits by category/role/context or confirms that in-policy spend auto-approves while only exceptions route to a human. Missing for 10: explicit documentation of policy-builder granularity (category/role/context), explicit auto-approval behavior for in-policy expenses, and independent/hands-on confirmation of the approval-routing logic.

   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “What's our company policy on rideshare, and which transactions from last month violate it?”
   • [claimed-docs] “Navan shows employees a "price to beat" for every hotel search — a smart target based on location, date, and demand that's under their poli…”
   • [claimed-docs] “Navan shows employees a "price to beat" for every hotel search — a smart target based on location, date, and demand that's under their polic…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Ramp—none0/10

   No evidence in the pack addresses data residency, regional storage options, or geographic control over where data is stored; evidence only covers API, MCP, CLI, and expense-management features.

   ⚑ flag

   Navan—none0/10

   No evidence anywhere in the pack about data residency, region selection, or data storage location controls for Navan's data or its AI/MCP features; the pack only covers MCP capabilities, API endpoints, pricing features, and travel booking experience.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Ramp—none0/10

   No evidence pack item addresses AI training data usage, opt-out controls, or data-privacy policies regarding model training; all evidence concerns product features (cards, expense management, MCP/CLI integrations) rather than data governance for AI training. Missing for 10: any privacy policy statement, opt-out mechanism, or documentation about AI training data usage.

   ⚑ flag

   Navan—none0/10

   No evidence in the pack addresses AI training data usage, opt-out controls, or data privacy policy regarding model training; all evidence covers MCP integrations, expense/travel features, and unrelated community complaints. Missing for 10: any explicit statement on AI/model training data usage, opt-out settings, or data retention/privacy commitments.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Ramp—none0/10

   No evidence pack items address data retention policies, deletion controls, or user-configurable data lifecycle settings for AI/agent-related data; the pack focuses on API/MCP/CLI functionality and expense automation, not privacy/retention controls.

   ⚑ flag

   Navan—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or user/admin ability to manage how long AI/assistant data is stored or how to delete it — the pack covers MCP querying, API surfaces, pricing features, and travel booking, but nothing on retention/deletion controls.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Ramp—none0/10

   No evidence in the pack addresses telemetry opt-out or usage-tracking controls for AI-native users; Ramp's documentation covers APIs, MCP, CLI, and expense features but nothing about telemetry settings.

   ⚑ flag

   Navan—none0/10

   No evidence in the pack addresses telemetry/usage-tracking opt-out settings for Navan or its AI/MCP features; all evidence covers MCP data access, expense/travel features, and pricing.

   ⚑ flag

Mileage perdiem

1. employeeLog mileage with map-based distance and claim per-diem rates without building the expense by hand

   weight 2 · round to Ramp
   Ramp✓fullclaimed7/10

   Ramp's own docs confirm automatic mileage calculation via Google Maps integration for reimbursements and automatic per-diem rate adjustment based on trip location/duration, directly matching the story's request for map-based mileage and per-diem claims without manual entry. Missing for 10: independent/hands-on verification of the mileage logging UX and per-diem claim flow, and no detail on how these integrate into a single expense submission step.

   • [claimed-docs] “Our integration with Google Maps keeps repayments precise with automatic mileage calculations.”
   • [claimed-docs] “Per diem shows exactly what you can purchase, and automatically adjusts based on trip location and duration.”
   • [claimed-docs] “Reimburse employees with confidence in more than 70 countries and 40 currencies, knowing they can be paid in two days or less in their local…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence covers Navan's MCP/API integrations, travel booking rewards, and generic 'receipt scanning' and 'manage expenses' pricing bullets, but nothing describes mileage tracking, map-based distance calculation, or automated per-diem rate application. Missing for 10: mileage logging with GPS/map distance capture, per-diem rate lookup/auto-application, any auto-build-expense-from-mileage workflow.

   ⚑ flag

Receipt capture

1. employeeSnap a photo or forward an email and the platform OCRs the receipt and files it against the right transaction

   weight 3 · round drawn
   Ramp~partialclaimed5/10

   Evidence confirms Ramp automatically captures receipts and applies OCR/coding when a card is swiped, with edits/submission via SMS, Slack, or Teams (ramp-docs-8, ramp-docs-32), and general OCR accuracy claims exist for bill-pay (ramp-docs-16). However, none of the evidence specifically describes an employee snapping a photo of a paper receipt or forwarding an email receipt that gets OCR'd and matched to a transaction — the described flow is card-swipe-triggered capture, not employee-initiated photo/email submission. Missing for 10: explicit documentation of photo-upload or email-forwarding receipt intake and its OCR matching to transactions, plus independent/hands-on confirmation.

   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [claimed-docs] “Ramp's OCR captures each detail and line item with 99% accuracy.”

   proof ↗⚑ flag

   Navan~partialclaimed5/10

   Docs mention 'Receipt scanning for on-the-go expenses' as a pricing-page feature bullet and API docs mention a 'receipts' surface, implying photo capture and filing against transactions, but there's no detail on OCR accuracy, email-forwarding capture, or automatic matching logic. Missing for 10: technical documentation of the OCR/email-forwarding pipeline, evidence of automatic transaction matching, and independent/hands-on confirmation of accuracy.

   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

Receipt matching

1. employeeReceipts match to card transactions automatically — with e-receipts pulled from integrations — and I get nudged only when one is genuinely missing

   weight 2 · round to Ramp
   Ramp~partialclaimed6/10

   Ramp documents automatic receipt capture and coding at swipe time, auto-approval when in policy, and reminders/nudges only for transactions with missing receipts or memos (ramp-docs-8, ramp-docs-13, ramp-docs-29, ramp-docs-32). However, there's no explicit evidence of e-receipts being pulled in from email/vendor integrations (e.g., Amazon, Lyft, Uber) as the story specifies. Missing for 10: documentation of e-receipt integrations sourcing receipts automatically, and independent/hands-on confirmation that nudges only trigger for genuinely missing receipts.

   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “Let Ramp send reminders for missing items or request repayments for you.”
   • [claimed-docs] “Find transactions with missing receipts or memos in the last 14 days and draft reminder messages I can send to the team.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence only mentions generic 'receipt scanning for on-the-go expenses' and receipts as an API surface, but nothing describes automatic matching of receipts to card transactions, e-receipt pull from integrations, or smart nudging only when genuinely missing.

   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

Domestic

1. employeeSubmit an out-of-pocket expense and get reimbursed by direct deposit in days, tracked from submission to payout

   weight 3 · round to Ramp
   Ramp✓fullclaimed7/10

   Ramp explicitly supports out-of-pocket reimbursements paid within two days or less in local currency across 70+ countries (ramp-docs-14), with automated receipt capture, submission via SMS/Slack/Teams, and policy-based auto-approval reducing manual expense reports (ramp-docs-8, ramp-docs-32). Approval workflows and reminders support the submission-to-payout tracking narrative (ramp-docs-10, ramp-docs-13). Missing for 10: explicit end-to-end status tracking UI/dashboard evidence for an individual employee, and independent/hands-on confirmation of the 2-day payout claim.

   • [claimed-docs] “Reimburse employees with confidence in more than 70 countries and 40 currencies, knowing they can be paid in two days or less in their local…”
   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “Let Ramp send reminders for missing items or request repayments for you.”

   proof ↗⚑ flag

   Navan~partialclaimed3/10

   Navan pricing page mentions it can 'manage expenses and issue reimbursements' and includes receipt scanning, but there is no evidence describing direct-deposit payout, a specific reimbursement timeline (days), or end-to-end tracking from submission to payout. missing for 10: direct deposit mechanism, reimbursement speed/SLA, submission-to-payout tracking/status visibility.

   • [claimed-docs] “Manage expenses and issue reimbursements”
   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “Unlimited policy and approval workflows”

   proof ↗⚑ flag

International

1. finance leadReimburse employees abroad in their local currency without running a separate international payments process

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp explicitly advertises reimbursing employees in 70+ countries and 40 currencies with local-currency payout in two days or less, directly matching the story, and this is embedded in its core reimbursement product rather than a separate process. Missing for 10: independent/hands-on verification of actual cross-border payout speed/accuracy and details on FX handling or fees.

   • [claimed-docs] “Reimburse employees with confidence in more than 70 countries and 40 currencies, knowing they can be paid in two days or less in their local…”

   proof ↗⚑ flag

   Navan—none0/10

   Evidence only shows generic reimbursement management (docs-8) with no mention of local-currency payouts, multi-currency support, or eliminating a separate international payment process for reimbursing employees abroad.

   • [claimed-docs] “Manage expenses and issue reimbursements”

   proof ↗⚑ flag

Budgets

1. finance leadAllocate budgets to teams and projects and have card limits and approvals actually enforce them

   weight 2 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp's documentation directly supports budget allocation to teams/projects with card controls that enforce them: custom virtual cards with per-team/vendor spend permissions (ramp-docs-11, ramp-docs-31), pre-spend enforcement of limits and blocked merchants/categories (ramp-docs-9), policy-grounded recommended approve/reject actions (ramp-docs-10), and role/amount-based notification workflows (ramp-docs-12). This covers allocation, limit enforcement, and approvals working together. Missing for 10: no independent/hands-on verification of enforcement accuracy, and no explicit 'budget' object/API distinct from card limits shown in evidence.

   • [claimed-docs] “Set submission requirements, enforce spend limits, and block risky merchants or categories all before spend happens.”
   • [claimed-docs] “All spend requests come with a recommended action grounded in your policies, budgets, and funds, so you can approve or reject in seconds.”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “Create personalized workflows that only notify the right people, based on spend amount or team role, and keep visibility high.”
   • [claimed-docs] “A finance team issues instant virtual cards for each software subscription with per-vendor spending limits, giving real-time visibility into…”
   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”

   proof ↗⚑ flag

   Navan~partialclaimed4/10

   Navan documents general 'unlimited policy and approval workflows' and card management/policy-limit features, and MCP queries can surface policy violations and approval status, implying some enforcement infrastructure exists. However, there is no direct evidence of budget allocation to specific teams/projects or of card limits being tied to those budgets and automatically enforced. Missing for 10: explicit budget-allocation-to-team/project feature docs, evidence that card limits are dynamically tied to allocated budgets, and any hands-on confirmation that approvals actually block over-budget spend.

   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “Card management — see which cards are active or inactive, how many cards a user has, and other card details.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”

   proof ↗⚑ flag

Dashboards

1. founderSee company spend in real time — by team, category, and merchant — the day it happens, not when statements land

   weight 3 · round to Ramp
   Ramp✓fullclaimed8/10

   Ramp captures spend in real time at swipe (receipt/memo/category auto-filled), issues cards with real-time spend tracking per team/vendor, and offers Transactions API/webhooks for real-time data feeds by team, category, and merchant. This directly matches the founder's need for same-day visibility rather than waiting on statements. Missing for 10: no independent/third-party corroboration or explicit dashboard screenshot evidence of a unified real-time cross-team/category/merchant view.

   • [claimed-docs] “Issue cards, attach controls, and watch spend in real time — physical for employee in-person spend, virtual for reusable payment details, or…”
   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “Create custom virtual cards and set permissions for everything from ad marketplace spend to remote work stipends, for individual teams or yo…”
   • [claimed-docs] “A finance team issues instant virtual cards for each software subscription with per-vendor spending limits, giving real-time visibility into…”
   • [claimed-docs] “Webhooks allow your application to receive real-time notifications about events that occur in your Ramp account.”
   • [claimed-docs] “You'll create an access token and call the Transactions API to retrieve transaction data.”

   proof ↗⚑ flag

   Navan✓fullclaimed7/10

   Navan's docs show spend can be queried by department, vendor/merchant, and category via MCP/API, and card transactions (including Navan-issued cards) are retrievable directly rather than waiting for statements, supporting near real-time visibility for founders. Missing for 10: explicit same-day latency claims for card feeds, a dedicated real-time dashboard description, and independent/hands-on corroboration of update speed.

   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Analyze spend data — query expenses, identify trends, and break down costs by department, vendor, or category.”
   • [claimed-docs] “Show me every flagged expense over $500 from Q1 that hasn't been approved yet, grouped by department.”
   • [claimed-docs] “Ask questions about policies, approval flows, and flag/decline reasons — understand why a transaction was flagged, who needs to approve it, …”
   • [claimed-docs] “OAuth 2.0 client-credentials flow, retrieval and update endpoints across the expense surface, custom-field management, receipts, and webhook…”

   proof ↗⚑ flag

Booking

1. employeeBook flights and hotels in-platform with travel policy applied at booking time, not expensed and argued about later

   weight 2 · round to Navan
   Ramp✓fullclaimed7/10

   Ramp Travel explicitly shows policy status at time of booking ('See policy status for every option... wondering if trips will get rejected'), applies per diem automatically, and even auto-rebooks hotels when rates drop, indicating in-platform booking with policy enforced upfront rather than post-hoc expense review. This directly matches the story of not having to expense-and-argue later. Missing for 10: independent/hands-on verification of the booking flow UX, and detail on flight booking specifically (most evidence focuses on hotel/per diem) plus confirmation of real-time policy blocking vs. just visibility.

   • [claimed-docs] “See policy status for every option. No digging through static policy PDFs or wondering if trips will get rejected.”
   • [claimed-docs] “Per diem shows exactly what you can purchase, and automatically adjusts based on trip location and duration.”
   • [claimed-docs] “Ramp monitors hotel rates and automatically rebooks if the price decreases by $50+.”

   proof ↗⚑ flag

   Navan✓fullclaimed8/10

   Navan's core booking product shows in-platform flight/hotel booking with policy limits enforced at search time ('price to beat' under policy, docs-12/27), self-serve booking with 24/7 support (docs-11), human travel agents that must confirm before booking (docs-14-16), and unlimited configurable policy/approval workflows applied to travel (docs-25) plus connected corporate cards for direct billing (docs-9) rather than post-hoc expensing. Missing for 10: independent/hands-on confirmation that out-of-policy bookings are actually blocked or flagged in real time (only vendor marketing/docs cited), and no detail on how policy violations are handled during the booking flow itself.

   • [claimed-docs] “Global travel inventory and exclusive rates”
   • [claimed-docs] “Self-serve changes and 24/7 travel support agents”
   • [claimed-docs] “Navan shows employees a "price to beat" for every hotel search — a smart target based on location, date, and demand that's under their poli…”
   • [claimed-docs] “Navan Edge provides 24/7 access to human travel agents via chat or phone at +1-877-536-3343 in English.”
   • [claimed-docs] “Navan Edge will always ask for your explicit confirmation before booking, changing, or canceling any trip.”
   • [claimed-docs] “Unlimited policy and approval workflows”
   • [claimed-docs] “Connect existing corporate or business credit cards”
   • [claimed-docs] “Navan shows employees a "price to beat" for every hotel search — a smart target based on location, date, and demand that's under their polic…”

   proof ↗⚑ flag

Trip expenses

1. employeeA trip's expenses — bookings, cards, receipts — collect themselves into one itinerary-linked report

   weight 1 · round to Navan
   Ramp~partialclaimed5/10

   Ramp documents automatic receipt capture and card-based expense coding (ramp-docs-8, ramp-docs-32) and travel-specific policy/per-diem/hotel tools (ramp-docs-18, ramp-docs-19, ramp-docs-20), suggesting trip spend is tracked and can be booked within policy, but there is no explicit documentation that bookings, cards, and receipts are automatically consolidated into a single itinerary-linked expense report for the employee. missing for 10: explicit description of a unified trip/itinerary report view, evidence that booking data auto-links to card transactions and receipts under one trip record, and any hands-on confirmation of this consolidation.

   • [claimed-docs] “As soon as you swipe your card, Ramp captures the receipt and fills in memos and categories. Make edits and submit via SMS, Slack, or Micros…”
   • [claimed-docs] “See policy status for every option. No digging through static policy PDFs or wondering if trips will get rejected.”
   • [claimed-docs] “Per diem shows exactly what you can purchase, and automatically adjusts based on trip location and duration.”
   • [claimed-docs] “Ramp monitors hotel rates and automatically rebooks if the price decreases by $50+.”
   • [claimed-docs] “the receipt is captured automatically, coded to the correct GL account, and auto-approved because it's within policy — no expense report fil…”

   proof ↗⚑ flag

   Navan~partialclaimed6/10

   Navan's own docs describe unified handling of card transactions, manual expenses, receipts, and reimbursements within a single platform/API (navan-docs-4, navan-docs-8, navan-docs-9, navan-docs-24), implying expenses converge into one system, but no evidence explicitly confirms automatic itinerary-linked report assembly from bookings+cards+receipts without manual reconciliation steps. Missing for 10: explicit documentation of automatic itinerary-to-expense-report linkage, and independent/hands-on confirmation that receipts and card charges auto-match to trip itineraries without manual effort.

   • [claimed-docs] “Retrieve and update Navan card transactions, Connect card transactions, manual expenses, payroll, repayments, fees, adjustments, daily rebat…”
   • [claimed-docs] “Manage expenses and issue reimbursements”
   • [claimed-docs] “Connect existing corporate or business credit cards”
   • [claimed-docs] “Receipt scanning for on-the-go expenses”
   • [claimed-docs] “Unlimited policy and approval workflows”

   proof ↗⚑ flag