Digits vs Mercury Books

Agent access

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

   weight 2 · round to Digits
   Digits✓fullprobed9/10

   Digits publishes both a top-level llms.txt (digits.com/llms.txt) and a developer-docs llms.txt (developer.digits.com/llms.txt), confirmed live via probe with HTTP 200, plus .md mirrors of every doc page — exactly the agent-oriented docs format the story asks for. missing for 10: independent third-party confirmation that an agent successfully consumed the llms.txt end-to-end (only first-party probes and docs are available).

   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.digits.com/llms.txt # Digits Connect API Documentation > Documentation for Digits Connect API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://developer.digits.com/docs/overview.md --- updatedAt: 2026-08-31T23:35:53.000Z --- Fetch the complete doc…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”

   proof ↗⚑ flag

   Mercury Books!disputedcontradicted2/10

   Mercury's blog promises a future MCP layer for agents, but direct probes show no llms.txt file (404) and no discoverable OpenAPI/agent-oriented docs at any candidate path, meaning there is currently nothing an agent could be pointed at. Missing for 10: a live llms.txt or agent-readable docs file, a shipped API/MCP endpoint, any evidence of the promised MCP layer actually existing.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Digits~partialprobed5/10

   Digits exposes a full programmatic REST API (OAuth 2.0, OpenAPI spec, batch sync with idempotent writes, webhooks) and a resettable developer sandbox, which supports scripted/automated use outside a GUI, and the MCP server is also a headless, auth-gated JSON-RPC endpoint. However, there is no explicit CI/CD documentation, no service-to-service (client-credentials) auth flow described, and OAuth authorization-code grant typically requires an initial interactive login step, so pure unattended CI automation isn't directly documented. Missing for 10: explicit CI/headless-automation guide, client-credentials or machine-to-machine auth flow, and independent confirmation of unattended pipeline use.

   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “"The Digits Connect API uses OAuth 2.0 with the authorization code grant type... API access in 3 steps: 1. User Authorization via https://co…”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly frames a full API and MCP layer as a future roadmap item ('Soon...'), and direct probes for API/OpenAPI/llms.txt endpoints all returned 404s, confirming no headless/CI-usable interface exists today. Command is a plain-language, in-app assistant, not a scriptable or automatable interface.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round drawn
   Digits—none0/10

   All MCP evidence describes Digits exposing itself AS an MCP server (api.digits.com/mcp) so that other AI tools like Claude, ChatGPT, or Cursor can pull Digits' financial data — the opposite direction from this story, which asks whether a user can plug external MCP servers INTO Digits so Digits' own AI (e.g. Ask Digits) can call their tools. No evidence shows Digits acting as an MCP client or supporting user-added MCP server connections.

   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The MCP launch post positions the ledger as the agent surface: Digits MCP "is now available as an official Claude Connector, making it even …”
   • [probe] “official MCP server documented at https://help.digits.com/firms-connections/digits-mcp”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The only MCP-related evidence is a forward-looking statement that an MCP layer is coming 'soon' to let external agents call Mercury Books' own actions — this describes Mercury exposing an MCP server, not the product consuming external MCP servers' tools, and it is explicitly not yet shipped (confirmed by 404 probes for API/openapi endpoints). There is no evidence users can plug third-party MCP servers into Mercury Books today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 3 · round to Digits
   Digits✓fullprobed9/10

   Digits ships a documented, hosted official MCP server at https://api.digits.com/mcp with OAuth against a user's own account, listed setup steps for Claude Desktop/Code, ChatGPT, Cursor, and Perplexity, and this is independently confirmed live via a probe showing a proper auth-gated JSON-RPC endpoint with RFC 9728 metadata. Missing for 10: broader independent third-party hands-on usage reports beyond the vendor docs and one live probe.

   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The MCP launch post positions the ledger as the agent surface: Digits MCP "is now available as an official Claude Connector, making it even …”
   • [probe] “official MCP server documented at https://help.digits.com/firms-connections/digits-mcp”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury only states that an MCP layer is coming 'soon' for AI agents, with no evidence it currently exists; probes for API/OpenAPI/llms.txt endpoints all return 404s, confirming no official MCP server is live today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Digits—none0/10

   Digits ships an OpenAPI spec, SDG codegen, and an MCP server, but nothing in the evidence pack documents an official Digits CLI tool for developers; the only CLI mentioned is Claude's own 'claude mcp add' command, which is a third-party client CLI, not Digits'.

   ⚑ flag

   Mercury Books—none0/10

   No evidence of a CLI; only future-planned API/MCP layer is mentioned, and probes for llms.txt/openapi endpoints returned 404s, indicating no current programmatic or CLI tooling exists.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 3 · round to Digits
   Digits✓fullprobed9/10

   Digits publishes a full public REST API (Connect API) with OAuth2 authorization-code flow, versioned routes, OpenAPI 3.0 spec, generated SDKs across 50+ languages, a free resettable developer sandbox, and documented read/write endpoints (ledger, statements, bills workflow, webhooks) — this is a comprehensive, documented, programmatically-drivable API confirmed live by independent probes. missing for 10: the raw openapi.json file itself 404'd on direct probe (docs reference it at /openapi rather than the paths tried), so full spec accessibility wasn't independently verified end-to-end.

   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “"The Digits Connect API uses OAuth 2.0 with the authorization code grant type... API access in 3 steps: 1. User Authorization via https://co…”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”
   • [claimed-docs] “"The Digits Connect API uses route-based versioning with the version number as a URL path prefix" — a published versioning policy on the dev…”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [probe] “PROBE docs-md: HTTP 200 at https://developer.digits.com/docs/overview.md --- updatedAt: 2026-08-31T23:35:53.000Z --- Fetch the complete doc…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.digits.com/openapi.json, https://developer.digits.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly says a full accounting API and MCP layer are coming 'soon,' not currently available, and direct probes for llms.txt and OpenAPI docs both returned 404s, confirming no public API exists today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Digits~partialprobed6/10

   The Connect API documents granular OAuth 2.0 scopes (e.g., 'source:sync ledger:read documents:write', 'bills:manage') that a developer/agent app can request, and the MCP server is fixed to read-only scope with its own OAuth flow, which together support least-privilege credential issuance. However there is no documented feature for a user to self-issue named, revocable API keys per-agent with custom scope selection (only the developer OAuth app flow, and the MCP server's scope is fixed read-only, not user-configurable). Missing for 10: dedicated 'create scoped API key for this agent' UI/API, per-agent revocation/audit trail, and evidence of narrower-than-read-only or custom scope combinations being selectable for MCP/agent use.

   • [claimed-docs] “"The Digits Connect API uses OAuth 2.0 with the authorization code grant type... API access in 3 steps: 1. User Authorization via https://co…”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence only mentions a future accounting API and MCP layer as 'soon' (not yet shipped), with no mention of API keys, OAuth scopes, or least-privilege credential issuance; probes confirm no OpenAPI/spec or docs endpoints currently exist. There is no evidence Mercury Books lets a user issue scoped credentials for an agent today.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Digits
   Digits~partialprobed5/10

   Digits documents a full OpenAPI 3.0 spec and offers OpenAPI-Generator based codegen for 50+ languages/frameworks, plus a developer sandbox and OAuth flow — enabling AI-native developers to build integrations — but there is no evidence of dedicated, first-party maintained SDK packages (e.g., official Python/Node/Go client libraries), and a probe for the raw OpenAPI file at common paths returned 404s, casting some doubt on spec accessibility. missing for 10: dedicated first-party SDK repositories/packages, confirmed live OpenAPI spec file, independent corroboration of codegen usage.

   • [claimed-docs] “The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response sc…”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.digits.com/openapi.json, https://developer.digits.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury explicitly frames the accounting API and MCP layer as future ('Soon'), and probes confirm no live OpenAPI/llms.txt endpoints exist yet — there is no official SDK currently available to build against.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to Digits
   Digits~partialclaimed6/10

   Digits' API reference documents webhook event delivery — "Digits sends this JSON request body to your configured webhook endpoint" — confirming a webhook mechanism exists for event notifications, which supports agentic/event-driven integration alongside the OAuth API and MCP server. However, evidence lacks detail on how a user subscribes/manages webhook endpoints (create/list/delete subscription endpoints), the catalog of event types, retry/signing/security details, or independent confirmation of reliability. Missing for 10: webhook subscription management API details, event type catalog, delivery guarantees/signing docs, and independent/hands-on verification.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence pack item mentions webhooks or event subscriptions; the only programmatic-access claim is a forward-looking 'soon' API/MCP mention, and probes confirm no public API/openapi spec exists yet. Missing for 10: any webhook documentation, event types, or subscription mechanism.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Digits
   Digits✓fullprobed8/10

   Digits ships 'Ask Digits' as an in-product AI assistant that answers financial questions and completes tasks ('Ask questions. Complete tasks. Understand your business'), plus AI-driven trend insights, exception surfacing, and quality-control checks embedded in dashboards and the Agentic Close workflow. This is corroborated by a live, auth-gated MCP server exposing the same ledger data for AI-generated insights externally, reinforcing the product's AI-native insight capability. Missing for 10: independent/hands-on user reviews validating the quality of Ask Digits' insights beyond vendor claims.

   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “Digits Dashboards provide real-time, customizable views of revenue, expenses, cash, and other key metrics so founders and finance teams alwa…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Command lets users ask natural-language questions about their financial data and get AI-grounded answers, plus AI-driven GL code suggestions and categorization, directly inside Books. missing for 10: independent/hands-on verification of insight quality, no detail on proactive suggestion generation beyond categorization/GL coding, and Mercury's own caveat that automation is not full autopilot.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”
   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Digits~partialclaimed7/10

   Digits documents strong built-in autonomous background processing: auto-booking 95%+ of transactions in real time, automated reconciliations, and an 'Agentic Close' workflow that continuously collects activity, books transactions, starts reconciliation, generates schedules, runs QC, and surfaces exceptions without user intervention. It also supports webhook event delivery and an 'Ask Digits' task mode. However, there's no evidence of user-configurable automation rules, triggers, or a workflow builder that an AI-native user could set up themselves — the automation is largely pre-built rather than user-defined. Missing for 10: user-configurable automation/trigger setup, scheduling controls, or evidence of custom rule-based automations beyond the fixed AGL pipeline.

   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”
   • [claimed-docs] “an AI-native month-end close workflow that collects financial activity continuously, books transactions inside the ledger, starts reconcilia…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books documents continuous, automatic categorization/reconciliation and a Command assistant that can be handed bookkeeping tasks in plain language (bulk GL coding, categorization rules), which is real background automation. However, the vendor itself explicitly cautions that 'a connected system isn't the same as fully automated' and that it should not be treated as 'putting your books on autopilot,' and the promised MCP/agent layer for end-to-end autonomous handling is described as 'soon,' not shipped. Missing for 10: a live, user-configurable autonomous automation/agent layer (MCP) with independent confirmation it runs unattended in production.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”

   proof ↗⚑ flag

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

   weight 3 · round to Mercury Books
   Digits~partialclaimed6/10

   Digits ships 'Ask Digits', a built-in AI assistant that answers financial questions and has a documented 'task mode' to 'Get it Done', which supports delegation of tasks within the product itself. However, evidence for the task-execution side is thin — only a marketing blurb, with no detailed docs, workflow examples, or independent/hands-on confirmation of what tasks it can actually complete autonomously. missing for 10: detailed documentation or hands-on evidence of the range/reliability of tasks Ask Digits can execute, independent corroboration of agentic task completion, and any limits/guardrails on delegated actions.

   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “Ask Digits Your AI financial assistant”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Books ships a built-in AI assistant called Command that users can query in plain language and delegate bookkeeping tasks to (journal entries, chart of accounts organization, bulk categorization), described as 'AI built-in, not bolted on.' Missing for 10: independent/hands-on verification of Command's task-delegation reliability, and the vendor's own caveat that automation isn't 'autopilot' tempers full agentic delegation claims.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Digits✓fullprobed7/10

   Digits ships "Ask Digits", an in-product AI assistant that lets users ask natural-language questions about financials and invoke a documented task mode ("Ask Digits to Get it Done") to complete actions, and additionally exposes an MCP server so natural-language agents in Claude/ChatGPT/Cursor can query live ledger data. Missing for 10: independent/hands-on verification that Ask Digits' task execution actually works as described, and clarification of how far natural-language commands can go given the MCP server is documented as read-only.

   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “Ask Digits Your AI financial assistant”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The MCP launch post positions the ledger as the agent surface: Digits MCP "is now available as an official Claude Connector, making it even …”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed7/10

   Mercury Command lets users ask questions and hand off bookkeeping tasks 'in plain language,' directly matching the natural-language command story, and this is documented across multiple first-party sources describing bulk actions, categorization, and Q&A. Missing for 10: independent/hands-on verification of Command's NL capabilities and confirmation that the broader agent-facing API/MCP layer (still described as 'soon') doesn't gate deeper command coverage.

   • [claimed-docs] “Ask Mercury Command a question about your books, or hand off a bookkeeping task to it directly, in plain language.”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Digits
   Digits~partialprobed6/10

   Digits publishes a full OpenAPI 3.0 spec, an interactive-friendly llms.txt/markdown mirror of docs, and a free resettable developer sandbox with demo data, which together support exploring the API with real requests; however, the probe found no hosted interactive reference UI (openapi.json/swagger.json paths 404'd) and no evidence of embedded runnable code examples within the docs themselves. missing for 10: a live interactive API-reference UI (e.g., Swagger/Redoc/Stoplight) with clickable 'try it' runnable examples, and confirmation that the OpenAPI spec is actually renderable/explorable rather than just downloadable.

   • [claimed-docs] “The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response sc…”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.digits.com/openapi.json, https://developer.digits.com/swagger.json, https://develo…”
   • [probe] “PROBE docs-md: HTTP 200 at https://developer.digits.com/docs/overview.md --- updatedAt: 2026-08-31T23:35:53.000Z --- Fetch the complete doc…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   There is no evidence of any interactive API reference or runnable examples; the API is described only as 'soon' coming, and probes for openapi/llms.txt specs both returned 404s, indicating no public API docs exist yet.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Digits✓fullprobed8/10

   Digits explicitly documents a 'complete OpenAPI 3.0 specification' covering all endpoints/params/schemas, hosted at a stated URL and paired with OpenAPI Generator codegen support for 50+ languages, plus a parallel llms.txt and per-page .md mirrors for machine-readable docs (digits-supp-openapi-llms, digits-docs-5, digits-probe-1, digits-probe-2). A probe attempting to fetch the spec failed, but it only tried guessed generic paths (openapi.json, swagger.json, etc.) rather than the actually documented '/openapi' URL, so this is not a concrete contradiction. Missing for 10: independent verification that the documented '/openapi' URL itself returns a valid spec live.

   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [claimed-docs] “The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response sc…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developer.digits.com/llms.txt # Digits Connect API Documentation > Documentation for Digits Connect API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://developer.digits.com/docs/overview.md --- updatedAt: 2026-08-31T23:35:53.000Z --- Fetch the complete doc…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.digits.com/openapi.json, https://developer.digits.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Direct probes for llms.txt and OpenAPI/Swagger spec files all return 404, and docs only mention a future accounting API/MCP layer as an upcoming feature, not something currently downloadable. No machine-readable API spec exists today.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”

   proof ↗⚑ flag

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

   weight 1 · round to Digits
   Digits✓fullclaimed8/10

   Digits documents a dedicated developer sandbox with a resettable demo instance pre-loaded with realistic data, entirely separate from production, and free/self-serve access via Development API keys that auto-select the demo client in OAuth. This directly satisfies testing without touching production data. Missing for 10: independent/hands-on confirmation that the sandbox behaves identically to production and covers write endpoints (e.g., bills workflow) without side effects.

   • [claimed-docs] “Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo …”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence of any sandbox, staging, or test environment for Mercury Books; the API/MCP layer is described only as forthcoming with no mention of a non-production mode, and probes for docs/OpenAPI endpoints returned 404s.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Digits~partialclaimed5/10

   Digits documents route-based API versioning (version number as URL path prefix) on a dedicated versioning docs page, showing intentional version management for AI/agent consumers of its Connect API and MCP server. However, no evidence describes an explicit deprecation policy (timelines, sunset notices, migration guidance for old versions) — missing for 10: documented deprecation timeline/process, evidence of past version sunsets, and confirmation this policy also covers the MCP server surface.

   • [claimed-docs] “The Digits Connect API uses route-based versioning with the version number as a URL path prefix.”
   • [claimed-docs] “"The Digits Connect API uses route-based versioning with the version number as a URL path prefix" — a published versioning policy on the dev…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The API is described as forthcoming ('Soon, a full accounting API will make every core Books action available programmatically'), and direct probes for openapi/llms.txt specs return 404s, showing no versioned API or deprecation policy currently exists.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Digits~partialclaimed6/10

   The Connect API documents batch transaction sync with external-ID idempotence ("Idempotence and deduplication is handled via the external_id field") and auto-books 95%+ of transactions in real time, showing the platform can process many items at once programmatically. However there's no documented bulk-edit UI, bulk categorization/reclassification endpoint, or explicit multi-item action beyond transaction sync and bill workflows. Missing for 10: dedicated bulk-update/bulk-edit endpoints or UI, evidence of bulk operations across other object types (invoices, reports, vendors) beyond transactions, and independent confirmation of batch scale limits.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”

   proof ↗⚑ flag

   Mercury Books~partialprobed6/10

   Mercury Command explicitly supports bulk actions like bulk GL code assignment, categorization rules, and clearing categorization backlogs in bulk, which directly addresses bulk operations for an AI-native user. However, this is limited to bookkeeping/categorization tasks rather than a general-purpose bulk API, and the promised full accounting API/MCP layer for broader programmatic bulk actions is only 'coming soon,' with probes confirming no public API/OpenAPI spec exists yet. missing for 10: a live public API or MCP layer enabling arbitrary bulk operations, independent/hands-on verification of bulk actions working at scale, and documentation of bulk operation limits or scope beyond categorization/GL codes.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 3 · round to Mercury Books
   Digits~partialclaimed3/10

   Digits offers webhook event delivery (JSON payloads on ledger events) and internal automated actions like auto-booking, flagging, and quality checks, but these are pre-built automations rather than a user-facing rule engine where an AI-native user can define custom 'if event X then action Y' triggers. Missing for 10: a documented rule-builder/automation configuration UI or API, examples of user-defined trigger-action pairs, and evidence of arbitrary custom actions being executed on arbitrary events beyond fixed webhook notifications.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Command explicitly supports creating 'categorization rules' and bulk GL code assignment, which is a form of user-defined rule-based automation triggered by transaction events, and automatic categorization/reconciliation is built-in. However, there's no evidence of a general-purpose rule/trigger-action framework beyond categorization (e.g., rules for invoicing, alerts, or other business events), and Mercury's own docs caution that automation isn't full autopilot. Missing for 10: broader event types beyond categorization, explicit rule configuration UI/API details, and independent confirmation of rule reliability.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Digits—none0/10

   Digits offers webhooks, background auto-booking, and month-end close automation, but there is no evidence of a user-facing scheduler for recurring jobs/workflows (e.g., cron-like triggers, scheduled report generation, or workflow automation builder) that an AI-native user could configure. missing for 10: any documented scheduling/cron API or UI, recurring job configuration, or workflow trigger system.

   ⚑ flag

   Mercury Books—none0/10

   Evidence shows automatic categorization/reconciliation and an AI assistant (Command) that can be asked to do tasks, but there is no mention of user-defined recurring/scheduled jobs or workflows; the API/MCP layer that might enable this is explicitly described as 'soon' (not yet shipped), and probes for API endpoints 404. Missing for 10: any documented scheduling/recurring-workflow feature, evidence of a live automation API or MCP layer, and independent confirmation of scheduled task execution.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Digits—none0/10

   Digits documents automated bookkeeping, auto-booking, agentic close, and exception surfacing, but nothing in the evidence describes versioning, reviewing change history, or rolling back automations/rules themselves — no changelog, rule-versioning, or undo mechanism for its automated workflows is documented.

   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “an AI-native month-end close workflow that collects financial activity continuously, books transactions inside the ledger, starts reconcilia…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Mercury Books has automation features (Command AI assistant, categorization rules, bulk GL code assignment) but nothing about versioning automation rules, reviewing changes, or rolling back automated actions/decisions. No audit trail, undo, or history/version-control feature is mentioned anywhere in the pack.

   ⚑ flag

Ai reconciliation

1. ai-native userHave an agent reconcile a month end-to-end, matching transactions, flagging exceptions, and preparing the close for human review

   weight 3 · round to Digits
   Digits~partialclaimed6/10

   Digits documents an 'Agentic Close' workflow that continuously books transactions, starts reconciliation before month-end, generates schedules, surfaces exceptions with context, and produces reports from the live ledger, plus 95%+ auto-booking and quality-control checks — strong first-party alignment with the story. However, this is all vendor-authored marketing/docs with no independent or hands-on verification of end-to-end autonomous execution, no example of an agent actually running a full close via API/MCP, and the MCP server is explicitly read-only (cannot book, flag, or take reconciliation actions itself), meaning the 'agent-driven' close is only demonstrated through the closed first-party product, not via the agent-facing surfaces. missing for 10: independent/hands-on evidence of an agent executing the full reconciliation-to-close workflow, and MCP/API write access enabling an external agent to perform booking/exception-flagging rather than just read data.

   • [claimed-docs] “an AI-native month-end close workflow that collects financial activity continuously, books transactions inside the ledger, starts reconcilia…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “Digits adds 11 new quality checks to make closing the books that much easier!”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books has continuous automatic reconciliation/categorization and Command can answer questions and offload bookkeeping tasks like journal entries and bulk categorization, but Mercury explicitly states automation is not 'autopilot' and requires human decision-making, and there's no evidence of an agent autonomously running a full month-end close with exception flagging and review prep end-to-end — the MCP/agent layer is only announced as 'soon'. missing for 10: evidence of an actual agent (not just Command chat) performing a full month-end close, explicit exception-flagging workflow, and a shipped MCP/API layer rather than a 'soon' roadmap item.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Bank feeds

1. founderConnect bank and credit-card accounts so transactions import automatically every day

   weight 3 · round drawn
   Digits✓fullclaimed8/10

   Digits documents real-time bank/credit-card connectivity across 12,000+ financial institutions with auto-booking of 95%+ of transactions in real time, and help docs describe adding new connections, positioning daily automatic import as a core feature. missing for 10: independent/hands-on confirmation of daily import reliability beyond vendor claims.

   • [claimed-docs] “"Digits Connect API seamlessly integrates with 12,000+ financial institutions, giving you real-time visibility into the metrics that matter—…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “Real-time Integrations 12,000+ financial institutions”
   • [claimed-docs] “Where do I add a new connection?”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports linking external bank accounts, cards, and payroll platforms with transactions pulled in automatically and reconciled/categorized continuously in real time, directly matching the founder story. Multiple first-party docs corroborate this (linking, auto-categorization, continuous reconciliation) and Mercury even publishes an honest caveat that 'connected' isn't 'fully automated,' showing transparency rather than contradiction. missing for 10: independent/hands-on verification beyond Mercury's own docs, and detail on daily import cadence/reliability guarantees.

   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Categorization

1. founderGet automatic categorization suggestions for imported transactions that learn from my corrections

   weight 2 · round to Mercury Books
   Digits~partialclaimed6/10

   Digits documents AI-native auto-categorization (AGL trained on 170M+ transactions, 95%+ auto-booking) and 'transaction flagging & smart reviews' suggesting a learning/correction loop, but there is no explicit documentation of a feedback mechanism where founder corrections are captured and used to retrain or adjust future suggestions. missing for 10: explicit description of a correction-feedback loop showing suggestions improve from user edits, independent/hands-on verification of accuracy improving over time, and details on how manual overrides are ingested by the categorization model.

   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “The AGL is a purpose-trained model suite: "Proprietary AI models trained on over 170 Million transactions totaling $875 Billion", doing "Rea…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury explicitly states that transactions are 'automatically assigned GL codes based on your categorization history and AI-driven suggestions,' directly supporting the idea of categorization suggestions that improve from past corrections, and Command lets users bulk-adjust GL codes and create rules that presumably feed this history. Mercury's own blog post also candidly notes automation has limits and isn't 'autopilot,' which sets realistic expectations rather than contradicting the feature. Missing for 10: independent/hands-on verification that suggestions specifically adapt after user corrections, and a public API/schema showing the correction-learning mechanism.

   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Reconciliation

1. accountantReconcile each bank account against the ledger with matched, unmatched, and duplicate transactions surfaced for review

   weight 3 · round drawn
   Digits~partialclaimed5/10

   Digits documents automated reconciliation, transaction flagging/smart reviews, and exception surfacing as part of its AI-driven bookkeeping and 'Agentic Close' workflow, which implies reconciliation review happens, but duplicates are described as being prevented via idempotent writes rather than surfaced as a reviewable duplicate queue. Missing for 10: explicit documentation of a per-bank-account reconciliation view distinguishing matched, unmatched, and duplicate transactions, and any hands-on/independent confirmation of this UI.

   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”
   • [claimed-docs] “Digits adds 11 new quality checks to make closing the books that much easier!”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Mercury Books claims accounts 'reconcile in real time' automatically with categorization pulled directly from linked banking data (mercury-books-supp-auto-rec, mercury-books-supp-launch), and Mercury's own honest-scope post acknowledges that full automation still requires human review of ambiguous decisions (mercury-books-supp-honest-scope), implying some reconciliation review workflow exists. However, none of the evidence specifically describes a UI or workflow that surfaces matched, unmatched, and duplicate transactions as distinct categories for accountant review — the emphasis is on automation eliminating manual reconciliation work entirely rather than a structured review interface. Missing for 10: explicit documentation of matched/unmatched/duplicate transaction states, a dedicated reconciliation review screen, and independent/hands-on confirmation of this workflow.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Bill management

1. accountantCapture vendor bills, route them for approval, and schedule payments from one workflow

   weight 2 · round to Digits
   Digits~partialclaimed7/10

   Digits documents a dedicated 'Bill Pay' feature (drag/drop/approve/pay) and a full bills workflow API covering ingest, query, submit, approve, pay, reject, and void gated by a bills:manage scope, which maps directly to capture, approval routing, and payment. However, evidence doesn't detail payment scheduling specifics (e.g., future-dated batch runs, approval chains/rules) or provide independent/hands-on confirmation the workflow works end-to-end. Missing for 10: explicit payment-scheduling mechanics, multi-step approval routing configuration details, and third-party corroboration.

   • [claimed-docs] “Bill Pay Drag. Drop. Approve. Pay.”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books~partialclaimed3/10

   Evidence only shows that 'bill pay' transactions are pulled into Mercury Books automatically alongside banking and invoicing data, implying some underlying bill-pay capability exists, but there is no description of a capture-to-approval-to-payment-scheduling workflow, approval routing, or scheduled payments within Books itself. missing for 10: vendor bill capture/OCR, approval routing rules, payment scheduling UI, evidence tying bill pay into an AP-specific workflow rather than just a transaction category.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Payables

1. accountantSee accounts payable aging and vendor balances at any point in time

   weight 2 · round to Digits
   Digits~partialclaimed7/10

   The developer API reference explicitly lists an 'accounts payable aging report' generator and a full bills workflow (ingest, query, submit, approve, pay, reject, void) gated by a bills:manage scope, implying vendor balance tracking within the AGL ledger. However, evidence doesn't explicitly confirm as-of-date/historical point-in-time snapshots for AP aging, and there's no independent/hands-on corroboration of the report's accuracy or usability. Missing for 10: explicit historical/point-in-time date parameter documentation, independent user validation of AP aging accuracy.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “Bill Pay Drag. Drop. Approve. Pay.”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence confirms Mercury Books generates P&L, cash flow, and balance sheet reports and mentions 'bill pay' as a data source, but there is no mention of an accounts payable aging report or vendor-balance tracking feature anywhere in the evidence pack. missing for 10: AP aging report, vendor balance report/ledger, point-in-time vendor balance lookups.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”

   proof ↗⚑ flag

Close process

1. accountantLock closed periods so prior-period numbers cannot change without an explicit reopening

   weight 2 · round drawn
   Digits—none0/10

   The evidence pack covers AGL categorization, the Agentic Close workflow, quality checks, and reporting, but nothing describes a period-lock or reopening-approval mechanism that prevents prior-period figures from changing. This is a reasonable axis for close-collaboration accounting software, so absence of evidence yields 'none'.

   ⚑ flag

   Mercury Books—none0/10

   No evidence in the pack mentions period locking, closing periods, or preventing edits to prior-period transactions without explicit reopening; the evidence covers categorization, reconciliation, reports, and accountant invites but not period lock controls.

   ⚑ flag

2. accountantRun a month-end close against a checklist that tracks reconciliations, accruals, and review sign-offs

   weight 3 · round to Digits
   Digits~partialclaimed6/10

   Digits documents an 'Agentic Close' workflow that starts reconciliation before month-end, generates accrual/depreciation schedules from ledger activity, runs quality-control checks, and surfaces exceptions with context, plus 11 dedicated closing quality checks — covering reconciliations, accruals, and QC review. However, there is no explicit documentation of a checklist UI or formal review/sign-off tracking (who approved what, sign-off status) as the story specifies. Missing for 10: an explicit close checklist artifact and documented sign-off/approval tracking mechanism.

   • [claimed-docs] “an AI-native month-end close workflow that collects financial activity continuously, books transactions inside the ledger, starts reconcilia…”
   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “Digits adds 11 new quality checks to make closing the books that much easier!”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows continuous automated reconciliation, accrual/cash accounting choice, and accountant collaboration via comments/tagging, but there is no mention of an actual month-end close checklist artifact, accrual entry tracking, or formal review sign-off workflow that an accountant could run through and mark complete. missing for 10: a defined close checklist feature, accrual scheduling/tracking, sign-off/approval workflow tied to close tasks.

   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Collaboration

1. founderInvite my external accountant or bookkeeper with role-scoped access to review and adjust the books

   weight 3 · round to Mercury Books
   Digits~partialclaimed6/10

   Digits documents collaboration features letting 'business owners, finance teams, and accountants review and share financials' (digits-docs-11) and firm-tier plans that add 'roles and permissions' and 'flexible client-level plans' (digits-supp-pricing), indicating some support for external accountant access. However, there is no concrete documentation of an invite flow, specific role scopes (e.g., view-only vs. edit/adjust), or how a founder specifically grants an external bookkeeper adjust-level access. missing for 10: detailed invite/role-management UI docs, granular permission levels for external accountants, and independent confirmation of the collaboration workflow.

   • [claimed-docs] “Digits Financials generates real-time, customizable financial statements and reports directly from the AGL with collaboration features that …”
   • [claimed-docs] “Published self-serve pricing, per business not per seat: "Yes, Digits offers a 30-day free trial", and "Digits generates real-time financial…”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports inviting bookkeepers/accountants in-product with role-tailored permissions and no seat caps, allowing them to view transactions, categorizations, and comment/tag on entries. Missing for 10: no independent/hands-on corroboration of the granularity of role-scoping (e.g., specific permission levels) and no detail on whether accountants can directly adjust vs. only comment.

   • [claimed-docs] “Invite your bookkeeper in-product, with unlimited seats at no extra cost.”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Data access

1. developerPull the full general ledger and trial balance through a documented API in open formats

   weight 3 · round to Digits
   Digits~partialprobed6/10

   Digits documents a full OpenAPI 3.0 spec, ledger endpoints including trial balance, balance sheet, P&L, and full chart of accounts retrieval, plus sandbox/dev environment access — satisfying most of the story. However, a live probe found the OpenAPI spec file itself returning 404 at all standard paths, and there's no explicit mention of exporting data in open/portable formats (e.g., CSV/JSON export of GL) beyond API JSON responses. missing for 10: working/reachable OpenAPI spec file (probe returned 404), explicit open-format export (CSV/JSON bulk export) of GL and trial balance, independent third-party confirmation of API completeness.

   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developer.digits.com/openapi.json, https://developer.digits.com/swagger.json, https://develo…”
   • [claimed-docs] “"Digits has a demo environment with realistic data pre-loaded from other connections. Each developer has access to their own resettable demo…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The evidence explicitly states a full accounting API is only planned ('Soon, a full accounting API will make every core Books action available programmatically'), and direct probes for OpenAPI/llms.txt docs returned 404s, confirming no current documented API for pulling GL/trial balance data in open formats.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

Integrations

1. founderConnect my banking, payments, and payroll systems so their activity flows into the ledger automatically

   weight 2 · round drawn
   Digits✓fullclaimed8/10

   Digits documents real-time connections to 12,000+ financial institutions with named payments/payroll connectors (Stripe, Gusto, Ramp), auto-booking 95%+ of transactions via the AGL, and idempotent sync with deduplication so activity flows automatically into the ledger. missing for 10: independent/third-party corroboration of actual bank/payroll sync reliability and no explicit named banking connector list beyond generic '12,000+ institutions' claim.

   • [claimed-docs] “"Digits Connect API seamlessly integrates with 12,000+ financial institutions, giving you real-time visibility into the metrics that matter—…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly supports linking external bank accounts, cards, and payroll platforms, plus named integrations with Stripe, PayPal, and Gusto, with activity flowing automatically into the ledger via continuous categorization and reconciliation. Mercury itself is candid that this is a strong starting point rather than full autopilot, which tempers but doesn't contradict the core claim. Missing for 10: independent/hands-on verification of these integrations working in practice, and a public API/OpenAPI spec was found to 404, indicating limited programmatic verification.

   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”

   proof ↗⚑ flag

Migration

1. founderMigrate historical books from another accounting system without losing transaction detail

   weight 1 · round to Digits
   Digits~partialclaimed4/10

   Digits has a help-center entry titled 'How do I migrate to Digits from Quickbooks?' and the Connect API supports idempotent, deduplicated transaction sync and chart-of-accounts fetch, suggesting some migration tooling exists, but no evidence details how historical transaction-level detail, account balances, or attachments are actually preserved during a full migration from another system. missing for 10: actual migration walkthrough/content beyond the FAQ title, evidence of historical balance/opening-balance handling, support for non-QuickBooks source systems, and independent confirmation that no transaction detail is lost.

   • [claimed-docs] “How do I migrate to Digits from Quickbooks?”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence describes an import/migration tool for bringing historical transaction-level data in from QuickBooks/NetSuite or other systems; in fact Mercury explicitly frames Books as a replacement rather than an integration/sync layer for prior accounting systems, and the cited third-party integrations (Stripe, PayPal, Gusto, bank feeds) are for ongoing data flow, not one-time historical migration.

   • [claimed-docs] “Does Mercury Books replace QuickBooks? Yes. Mercury Books is a complete accounting system — not an add-on or integration layer for another p…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”

   proof ↗⚑ flag

Invoicing

1. founderCreate and send invoices with online payment options and see when they are viewed and paid

   weight 3 · round to Digits
   Digits~partialclaimed3/10

   Digits' product page lists an 'Invoicing — Get paid faster' feature, confirming the axis applies, but there is no documentation describing invoice creation workflow, online payment integration, or read/paid status tracking. missing for 10: details on invoice creation UI, supported payment methods/gateways, view-tracking or paid notifications, and any independent confirmation of the feature working.

   • [claimed-docs] “Invoicing Get paid faster”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence only mentions 'invoicing' as one of many transaction types Mercury Books pulls in automatically (alongside banking, bill pay); there is no evidence of invoice creation/sending, online payment collection, or view/paid status tracking within Mercury Books itself.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Third-party data flows in alongside Mercury's own: Books "connects to a growing set of third-party platforms, including Stripe, PayPal, and …”

   proof ↗⚑ flag

2. founderSet up recurring invoices and automatic payment reminders for overdue customers

   weight 2 · round to Digits
   Digits~partialclaimed2/10

   Digits' product page lists an 'Invoicing — Get paid faster' feature and the Connect API exposes A/R aging reports, but there is no documentation of recurring invoice scheduling or automatic overdue-payment reminders. missing for 10: documented recurring invoice setup, automated reminder/dunning workflow, any hands-on or independent confirmation of these AR automation features.

   • [claimed-docs] “Invoicing Get paid faster”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The evidence pack mentions invoicing only as one data stream feeding into books (transactions across 'banking, invoicing, bill pay'), but there is no mention of recurring invoice scheduling or automated overdue payment reminders anywhere in the docs. This is a fair capability for a full accounting system to offer, so absence of evidence is 'none' rather than 'na'.

   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Link external bank accounts, cards, payroll platforms, and more for the complete story of your business.”

   proof ↗⚑ flag

Receivables

1. accountantTrack accounts receivable with aging reports and per-customer balances

   weight 2 · round to Digits
   Digits~partialclaimed6/10

   Docs confirm an accounts payable aging report and A/R aging generation via the API ('Generate an accounts payable aging report', A/R aging) plus per-customer/vendor ledger queries and chart of accounts access, and Digits Financials/Dashboards surface real-time reports; but there is no dedicated UI walkthrough or independent confirmation of a per-customer AR balance view or dunning/aging workflow in the product itself, only API-level mentions in the developer llms.txt. missing for 10: hands-on/UI evidence of an AR aging report screen, per-customer balance breakdown in the app UI, independent verification of accuracy/usability.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “Digits Financials generates real-time, customizable financial statements and reports directly from the AGL with collaboration features that …”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury Books documents P&L, cash flow, and balance sheet reports and mentions invoicing as one of the pulled-in transaction types, but no evidence describes accounts-receivable aging reports or per-customer balance tracking specifically. missing for 10: AR aging report feature, per-customer balance view, any invoicing/AR-specific reporting documentation.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”

   proof ↗⚑ flag

Ai ledger

1. ai-native userHave an agent draft and post journal entries via the API and leave them in a review queue for my accountant

   weight 3 · round to Digits
   Digits~partialclaimed5/10

   The Connect API documents write/batch transaction sync with external_id idempotence and a bills workflow with submit/approve/reject/void steps (a review-queue-like pattern), and OAuth scopes include ledger:write-style scopes, showing agents can post financial data programmatically. However, there is no explicit documentation of a 'draft journal entry' state or an accountant-facing review queue specifically for journal entries (as opposed to bills), and the MCP server—the more natural agent surface—is explicitly read-only, so agentic posting must go through the raw Connect API rather than a documented review workflow. Missing for 10: explicit journal-entry draft/pending state, an accountant review-queue UI/API for entries, and confirmation that MCP or agent tooling can trigger this flow.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"The Digits Connect API uses OAuth 2.0 with the authorization code grant type... API access in 3 steps: 1. User Authorization via https://co…”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”

   proof ↗⚑ flag

   Mercury Books—none0/10

   The only mention of a programmatic API and MCP layer for agents is explicitly framed as a future roadmap item ('Soon, a full accounting API... will let AI agents handle bookkeeping tasks end-to-end'), not a shipped capability, and probes confirm no live OpenAPI/MCP endpoints exist today (404s on all candidate paths). While Command can draft journal entries via chat and accountants can be invited to collaborate, there is no evidence of an API-driven posting workflow or a formal 'review queue' gating agent-drafted entries for accountant approval.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Accountant collaboration without seat caps: "You can invite your bookkeeper or accountant directly to your Mercury account with permissions …”

   proof ↗⚑ flag

Chart of accounts

1. accountantCustomize the chart of accounts with account types, sub-accounts, and class or tag dimensions

   weight 3 · round to Mercury Books
   Digits~partialclaimed4/10

   Digits documents the ability to fetch the full chart of accounts via the Connect API and mentions 'dimensional accounting'/'dimensional reporting' as a paid-tier feature, suggesting some support for class/tag dimensions, but there is no documentation of an accountant-facing workflow for creating account types or sub-accounts — indeed Digits' messaging emphasizes that its AI 'replaces' manual chart-of-accounts mapping rather than supporting granular manual customization. Missing for 10: explicit UI/API support for defining account types, creating/nesting sub-accounts, and configuring custom class or tag dimensions beyond the vague 'dimensional accounting' mention.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “Published self-serve pricing, per business not per seat: "Yes, Digits offers a 30-day free trial", and "Digits generates real-time financial…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Evidence shows GL code assignment, bulk categorization rules, and Class/tag attachment to transactions (via enriched QuickBooks/NetSuite integrations), plus Command's ability to help 'organize your chart of accounts' — indicating some COA customization exists. However there's no explicit documentation of defining account types or creating sub-accounts within the ledger structure itself. missing for 10: explicit account-type configuration, sub-account creation/hierarchy, and native (non-integration) class/tag dimension setup.

   • [claimed-docs] “Use Mercury Command to bulk assign GL codes, create categorization rules, and more”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “The banking side feeds clean data to any ledger: "Transactions on Mercury are now automatically assigned GL codes based on your categorizati…”

   proof ↗⚑ flag

Journal entries

1. accountantPost manual journal entries with balanced debits, credits, and supporting memos

   weight 3 · round to Mercury Books
   Digits—none0/10

   Digits' evidence describes AI-driven auto-booking, categorization, reconciliation, and an API for batch transaction sync/ledger queries, but nowhere documents a manual journal-entry workflow with debit/credit balancing and memo fields — the product's own framing explicitly positions itself as replacing manual entry/mapping rather than supporting it.

   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “The AGL is a purpose-trained model suite: "Proprietary AI models trained on over 170 Million transactions totaling $875 Billion", doing "Rea…”

   proof ↗⚑ flag

   Mercury Books~partialclaimed5/10

   Books is confirmed as a double-entry accounting system with journal entries as a core capability ("writing journal entries" is explicitly listed as a task Command can help with), implying balanced debit/credit posting, but there's no direct documentation of a manual journal-entry UI, memo/note fields, or debit=credit validation for accountant-initiated entries — most journal entry evidence frames it as an AI-assisted/automated task rather than manual accountant entry. Missing for 10: explicit manual entry screen documentation, memo/attachment support on journal entries, and confirmation of balance validation.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”

   proof ↗⚑ flag

Ai audit

1. ai-native userHave an agent monitor the ledger and flag anomalies in spend or duplicate transactions before the close

   weight 3 · round to Digits
   Digits~partialclaimed6/10

   Digits documents built-in anomaly/duplicate handling (idempotent writes with external_id dedup, 11 quality checks before close, 'Agentic Close' that 'surfaces exceptions with context', and 24/7 bookkeeping with 'transaction flagging & smart reviews'), and its MCP server lets an AI agent query the live ledger. However this is largely automated system-level checking rather than a user-directed agent actively monitoring and proactively flagging anomalies/duplicates during the close cycle, and the MCP server is explicitly read-only so an agent cannot act on or resolve flagged items. Missing for 10: independent/hands-on evidence that an AI agent can be configured to continuously monitor and alert on spend anomalies or duplicates specifically before close, and confirmation the flagging pipeline is agent-driven rather than purely rule/ML-based backend automation.

   • [claimed-docs] “"The Agentic Close — From transaction to close. One system. Most accounting systems only record work. The Agentic Close does it for you." Th…”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “Digits adds 11 new quality checks to make closing the books that much easier!”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The MCP launch post positions the ledger as the agent surface: Digits MCP "is now available as an official Claude Connector, making it even …”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Command can answer questions and bulk-categorize/reconcile transactions, and an MCP layer for agents is only promised as 'soon,' but nothing describes proactive anomaly detection, duplicate-transaction flagging, or pre-close audit alerts.

   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag

Audit trail

1. accountantSee a complete audit trail of who changed what and when across the entire ledger

   weight 3 · round drawn
   Digits—none0/10

   No evidence exists of a change-log, version history, or 'who changed what and when' audit trail feature across the ledger; the pack covers categorization, APIs, MCP, security-at-rest, and pricing but nothing about audit trails or user-action logging.

   ⚑ flag

   Mercury Books—none0/10

   No evidence describes an audit trail, change log, user attribution, or history of edits across the ledger; the pack focuses on automation, categorization, reporting, and accountant seat invites, none of which document who-changed-what-when tracking. This is a plausible and expected feature for a full accounting system, so absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

Multi entity

1. accountantManage multiple legal entities and produce consolidated financials across them

   weight 2 · round drawn
   Digits—none0/10

   Evidence shows Digits is built around a single AI-native general ledger (AGL) per business, with firm plans offering multi-client seats/permissions but no documented feature for combining multiple legal entities into consolidated financial statements. Nothing in the docs, API reference, or product pages mentions inter-entity eliminations, consolidated reporting, or multi-entity ledger structures.

   • [claimed-docs] “Published self-serve pricing, per business not per seat: "Yes, Digits offers a 30-day free trial", and "Digits generates real-time financial…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack mentions multiple legal entities, inter-company eliminations, or consolidated financial statements across entities; all documentation describes a single-business books setup with one set of P&L/balance sheet/cash flow reports.

   ⚑ flag

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

   weight 2 · round to Digits
   Digits~partialclaimed6/10

   The Connect API exposes substantial read/write ledger functionality (financial statements, chart of accounts, bills workflow with submit/approve/pay, batch transaction sync, webhooks) matching much of the UI's bookkeeping/reporting features, and the MCP server extends programmatic access to AI tools. However, the MCP server is explicitly read-only, and several UI-surfaced features (Ask Digits AI assistant, Invoicing, Bill Pay drag-and-drop UI, Dashboards customization, mobile app features) have no documented API/MCP equivalent for full parity — missing for 10: write access via MCP, API coverage for Ask Digits conversational tasks, invoicing endpoints, dashboard customization API, and independent confirmation that all UI actions map to API calls.

   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “"The Digits Connect API uses OAuth 2.0 with the authorization code grant type... API access in 3 steps: 1. User Authorization via https://co…”
   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “Bill Pay Drag. Drop. Approve. Pay.”
   • [claimed-docs] “Invoicing Get paid faster”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury's own docs say a full accounting API is coming 'soon' — it does not exist yet — and probes for llms.txt/openapi specs both return 404, confirming no current API parity with the UI.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 3 · round to Digits
   Digits~partialclaimed4/10

   Digits' Connect API exposes read endpoints for financial statements, chart of accounts, ledger entries, and transactions via a documented OpenAPI spec, which could be used to pull data out into open formats. However, there is no documented bulk 'export all your data' feature, no CSV/GDPR-style data portability statement, and no mention of account closure or migrating away from Digits (only migration into Digits from QuickBooks is documented). missing for 10: a dedicated full-account data export/download feature, explicit open-format (CSV/JSON) bulk export tooling, and any documentation addressing leaving/closing an account with full data portability.

   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"The Digits Connect API provides a complete OpenAPI 3.0 specification that describes all available endpoints, request parameters, response s…”
   • [claimed-docs] “How do I migrate to Digits from Quickbooks?”

   proof ↗⚑ flag

   Mercury Books—none0/10

   No evidence pack item mentions any data export feature, open format (CSV/OFX/JSON) download, or account-closure data portability path; the only related probes (llms.txt, openapi.json) return 404s, and Mercury explicitly positions Books as a replacement system rather than an interoperable one ('not an add-on or integration layer for another platform').

   • [claimed-docs] “Does Mercury Books replace QuickBooks? Yes. Mercury Books is a complete accounting system — not an add-on or integration layer for another p…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Digits—none0/10

   No evidence anywhere in the pack mentions data residency, regional data storage options, or geographic controls for where financial data is hosted; security page only discusses encryption and SOC 2, not location choice.

   ⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack discusses data residency, region selection, or storage location controls for Mercury Books; the material covers accounting features, AI assistant capabilities, and integrations only.

   ⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Digits—none0/10

   The evidence pack covers OAuth authentication, encryption at rest/in transit, and general security posture, but nothing addresses data retention policies or user-initiated deletion of financial data/records. For a financial ledger handling sensitive data, this is a fair and applicable privacy axis, but no documentation, help-center article, or API endpoint for retention settings or deletion requests is cited.

   ⚑ flag

   Mercury Books—none0/10

   The evidence pack contains no mention of data retention policies, deletion controls, export/purge mechanisms, or any privacy-posture settings a user could control; it focuses entirely on accounting features, AI assistant capabilities, and pricing. This is a fair axis for a financial SaaS product handling sensitive business data, but no supporting evidence exists.

   ⚑ flag

Ai insights

1. ai-native userAsk an agent "can we afford X?" and get an answer grounded in live ledger data pulled through the API

   weight 3 · round to Digits
   Digits✓fullprobed9/10

   Digits ships both a documented Connect API (OAuth, OpenAPI, live ledger endpoints for statements, balances, cash flow) and an official read-only MCP server exposing the 'live, auto-booked' AGL data to Claude, ChatGPT, Cursor etc., independently confirmed live via a working OAuth-gated MCP probe — enabling an agent to query real-time financial data to answer affordability-style questions grounded in the ledger. The Ask Digits assistant further demonstrates first-party natural-language grounding against live financials. Missing for 10: no independent third-party example of a real 'can we afford X' query/answer being run end-to-end through the API or MCP.

   • [claimed-docs] “The Digits MCP server is hosted at a documented endpoint — "Connect Digits to your AI tool using the steps below. Each tool may look a littl…”
   • [claimed-docs] “The MCP launch post positions the ledger as the agent surface: Digits MCP "is now available as an official Claude Connector, making it even …”
   • [probe] “PROBE mcp-oauth (2026-09-16): keyless JSON-RPC initialize to https://api.digits.com/mcp answers HTTP 401 with a www-authenticate Bearer chal…”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “"Meet Ask Digits — Ask questions. Complete tasks. Understand your business... Ask Digits anything about your financials—cash flow, expenses,…”
   • [claimed-docs] “auto-booking 95%+ of transactions in real time, delivering always up-to-date financials”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Mercury's own docs frame the accounting API and MCP layer for external agents as a future ('Soon') capability, not something shipped today, and direct probes for an OpenAPI spec or llms.txt on Mercury's docs return 404s, indicating no live API for third-party agents yet. The only grounded Q&A shown (Command) is an in-product assistant, not an externally callable API an outside agent could query.

   • [claimed-docs] “Soon, a full accounting API will make every core Books action available programmatically, and an MCP layer will let AI agents handle bookkee…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.mercury.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.mercury.com/openapi.json, https://support.mercury.com/swagger.json, https://support.…”
   • [claimed-docs] “The built-in AI assistant is Command: "Ask Command anything about your finances — spend, trends, GL codes — and get immediate answers ground…”

   proof ↗⚑ flag

Custom reports

1. accountantBuild custom reports filtered and grouped by class, location, or tag dimensions

   weight 2 · round to Digits
   Digits~partialclaimed5/10

   Digits explicitly advertises 'dimensional reporting' and 'dimensional accounting' as a feature (gated to Core/Pro plans) and has a help doc titled 'How do I create a custom report?', suggesting some custom, dimension-based reporting capability exists. However, no evidence specifies filtering/grouping by class, location, or tag dimensions specifically, nor shows a UI walkthrough or hands-on confirmation of this granularity. Missing for 10: explicit documentation naming class/location/tag as filterable/groupable dimensions, a hands-on or independent demonstration of building such a custom report, and detail on how grouping/filtering works in the report builder.

   • [claimed-docs] “providing real-time categorization, automated reconciliations, live connected financial data, dimensional reporting, cash flow and runway tr…”
   • [claimed-docs] “How do I create a custom report?”
   • [claimed-docs] “"24/7 AI Bookkeeping & Reconciliation — Books that keep themselves": "Digits AI learns your business to provide 24/7 bookkeeping with transa…”
   • [claimed-docs] “Published self-serve pricing, per business not per seat: "Yes, Digits offers a 30-day free trial", and "Digits generates real-time financial…”

   proof ↗⚑ flag

   Mercury Books—none0/10

   Evidence shows Mercury Books generates standard P&L, cash flow, and balance sheet reports, and mentions attaching 'Classes' to transactions only for customers with enriched QuickBooks/NetSuite integrations — not a native custom report builder. No evidence of location or tag dimensions, or of building custom reports filtered/grouped by these dimensions within Books itself.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “Customers with enriched integrations to QuickBooks and NetSuite can now attach Classes to transactions on Mercury.”

   proof ↗⚑ flag

Statements

1. founderGenerate an accurate P&L, balance sheet, and cash-flow statement for any period on demand

   weight 3 · round drawn
   Digits✓fullclaimed8/10

   Digits explicitly generates P&L, balance sheet, and cash-flow statements on demand from its live AGL ledger, with API endpoints for 'Generate a balance sheet statement', cash flow, and P&L, plus dashboards and custom reports (help.digits.com custom report doc). Pricing page confirms 'real-time financial statements—profit & loss, balance sheet, and cash flow' updating automatically. Missing for 10: independent/hands-on verification of statement accuracy for arbitrary custom periods, and no third-party review confirming report correctness beyond vendor claims.

   • [claimed-docs] “Digits Financials generates real-time, customizable financial statements and reports directly from the AGL with collaboration features that …”
   • [claimed-docs] “The API reference (indexed in the developer llms.txt) spans read AND write ledger surfaces: financial statements on demand ("Generate a bala…”
   • [claimed-docs] “Published self-serve pricing, per business not per seat: "Yes, Digits offers a 30-day free trial", and "Digits generates real-time financial…”
   • [claimed-docs] “How do I create a custom report?”
   • [claimed-docs] “"The Digits Connect API gives you programmatic access to the AGL® — our AI-native general ledger. Legacy accounting APIs expect you to sync …”

   proof ↗⚑ flag

   Mercury Books✓fullclaimed8/10

   Mercury Books explicitly generates P&L, cash-flow, and balance-sheet reports on demand from real-time reconciled data, with cash/accrual choice, positioned as a full double-entry replacement for QuickBooks. This is a core advertised feature with detailed first-party docs, though there's no independent/hands-on corroboration of report accuracy and Mercury itself cautions that automation isn't fully hands-off. Missing for 10: independent verification of statement accuracy, and confirmation that reports are audit-grade/error-free in practice.

   • [claimed-docs] “Generate P&L, cash flow, and balance sheet reports from today’s numbers, not last quarter’s.”
   • [claimed-docs] “Mercury Books is "Double-entry accounting that pulls directly from your Mercury data", generating "P&L, cash flow, and balance sheet reports…”
   • [claimed-docs] “From the launch post: "All your transactions across banking, invoicing, bill pay, and more are pulled in automatically as you build your bus…”
   • [claimed-docs] “Reconciliation and categorization are automatic and continuous: "Data across banking, cards, invoicing, and more are categorized automatical…”
   • [claimed-docs] “Mercury's own honest framing of automation limits: "a 'connected' system isn't the same as fully automated. Bank-connected bookkeeping can e…”

   proof ↗⚑ flag