Kick vs Mercury Books

Agent access

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

   weight 2 · round to Kick
   Kick✓fullprobed8/10

   A live llms.txt index exists at docs.kick.co/llms.txt (HTTP 200, confirmed by probe) with markdown mirrors and a documented ask-query interface, plus a real MCP JSON-RPC endpoint for docs search, giving agents multiple ways to consume agent-oriented documentation. missing for 10: this is a GitBook platform surface rather than a Kick-built capability, and there's no independent (non-vendor) corroboration of agents actually using it successfully.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.kick.co/llms.txt # Kick Docs ## Business Owners - [Kick Docs for Business Owners](https://docs.ki…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   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 drawn
   Kick—none0/10

   No evidence of an API, CLI, or headless automation surface for actual Kick operations: OpenAPI/swagger probes all 404, and the only live MCP endpoint found is a GitBook docs-search server, not a Kick account/ledger API. The single 'MCP/CLI' mention on the pricing page is a bare link with no supporting documentation of scriptable/CI-usable functionality.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “MCP/CLI”

   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
   Kick—none0/10

   There is no evidence that Kick lets users plug external MCP servers into the product so it can call their tools. The only MCP-related evidence is a GitBook-provided docs-search MCP endpoint (serving documentation, not Kick data or actions) and a separate workflow where Kick data is exported to Google Sheets for AI tools to read — neither shows Kick acting as an MCP client consuming external servers.

   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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 drawn
   Kick—none0/10

   The only MCP endpoint found is a generic GitBook platform docs-search server (serverInfo "mcp-typescript server on vercel"), explicitly noted as serving documentation, not Kick account data or ledger actions — not an official Kick-built MCP server. Kick's documented AI workflow instead routes through Google Sheets exports for LLMs, with no first-party MCP server for agent access to financial data or actions.

   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”

   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
   Kick—none0/10

   No evidence of a Kick-built CLI exists; the only 'CLI' mention is an unresolved label on a pricing page, and the actual agent-facing surfaces documented (GitBook llms.txt, GitBook MCP endpoint, Google Sheets AI workflow) are docs-search or spreadsheet integrations, not a command-line interface for interacting with Kick. missing for 10: any documented CLI tool, install instructions, command reference, or hands-on confirmation of a Kick CLI.

   • [claimed-docs] “MCP/CLI”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   proof ↗⚑ 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 drawn
   Kick—none0/10

   No documented public API for driving Kick itself was found: an OpenAPI/API probe returned 404s everywhere, and the only working MCP endpoint is explicitly a GitBook docs-search server that 'serves documentation, not Kick account data or ledger actions.' The AI integration path is one-way reporting into Google Sheets for LLMs to read, not a programmatic API to act on the product.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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 drawn
   Kick—none0/10

   No evidence of any API credential system, scoped tokens, OAuth grants, or agent-specific permission levels for Kick's product/account data—only role-based access control for human team members and a documentation-search MCP endpoint unrelated to account access. No mention of issuing least-privilege API keys or credentials for AI agents to act on a user's financial data.

   • [claimed-docs] “Kick uses role-based access control so you decide exactly who can see and do what in your workspace.”
   • [claimed-docs] “"All data transmitted to and from Kick is encrypted in transit using TLS. Data at rest is encrypted using AES-256... Kick connects to your f…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”

   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 drawn
   Kick—none0/10

   There is no evidence of an official Kick SDK: the OpenAPI/Swagger probe returned 404 on all candidate paths, and the only MCP endpoint found (kick-probe-3) is GitBook's generic docs-search MCP server, not a Kick-built API/SDK — it serves documentation, not account or ledger data. AI workflows are routed indirectly through Google Sheets exports rather than a programmable SDK.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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 drawn
   Kick—none0/10

   No evidence anywhere in the pack of a webhooks feature or event subscription mechanism for Kick account/ledger data; the only outbound integrations mentioned are docs-search MCP (GitBook platform) and Google Sheets sync, neither of which is a webhook subscription API.

   ⚑ 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 Mercury Books
   Kick~partialprobed4/10

   Kick documents AI categorization of transactions (auto-labeling ~97% on first pass, confidence-gated, learns from corrections) and real-time P&L updates from that AI action, which is a form of AI acting on user data. However, this is transactional automation, not explicit 'insights and suggestions' (e.g., anomaly flags, forecasts, recommendations) surfaced inside the product itself; the only place data is 'reasoned over' by AI (Gemini/Claude/ChatGPT) is via export to Google Sheets, which is outside the core product UI. Missing for 10: in-app AI-generated insights/recommendations dashboard, proactive suggestions beyond categorization, and evidence of AI reasoning happening natively within Kick rather than via Sheets/GitBook docs-search surfaces.

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.kick.co/llms.txt # Kick Docs ## Business Owners - [Kick Docs for Business Owners](https://docs.ki…”

   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 Mercury Books
   Kick~partialprobed4/10

   Kick automates categorization, transfer matching, reconciliation checks, and rule-based overrides continuously in the background (kick-supp-categorization, kick-supp-reconciliation, kick-docs-7), which is a form of autonomous background automation for bookkeeping tasks. However, this is limited to Kick's own fixed bookkeeping pipeline, not a general-purpose, user-configurable automation/agent framework that an AI-native user could set up for arbitrary autonomous tasks. missing for 10: evidence of user-defined autonomous workflows/agents beyond built-in categorization rules, a scheduling/trigger system for custom automations, or an automation builder — none is documented; MCP surfaces found are docs-search only, not action-capable agents.

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”
   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   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
   Kick~partialprobed4/10

   Kick documents AI automation for bookkeeping (auto-categorization with confidence gating, described as 'self-driving' per llms.txt) and logs AI actions in an audit trail, but this is background automation of a fixed task, not a conversational assistant a user delegates arbitrary tasks to. The actual 'ask an AI' workflow routes through external tools (Gemini/Claude/ChatGPT) reasoning over exported Sheets data, not a built-in assistant inside Kick's own UI. Missing for 10: a native in-product chat/assistant interface, evidence of delegating open-ended tasks (not just categorization) to it, and independent confirmation of this workflow beyond vendor docs.

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.kick.co/llms.txt # Kick Docs ## Business Owners - [Kick Docs for Business Owners](https://docs.ki…”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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 to Mercury Books
   Kick~partialprobed4/10

   Kick supports AI-native interaction only indirectly: reports sync as live data to Google Sheets so Gemini/Claude/ChatGPT can read, reason over, and even write back to the sheet, and the docs are agent-legible via GitBook's MCP/llms.txt surfaces. But there's no evidence of a native chat/NL command interface inside Kick itself for issuing commands like 'recategorize this transaction' or 'send this invoice' — the MCP endpoint found only serves documentation search, not account actions, and AI categorization is automatic/rule-based rather than user-prompted NL commands. Missing for 10: a first-party NL command interface or agent that can execute ledger/invoicing/bill-pay actions directly from user prompts, and independent corroboration of the write-back capability actually altering Kick data (not just the sheet).

   • [claimed-docs] “Your Kick reports land as live spreadsheet data in your workbook, so Gemini, Claude, or ChatGPT can read and reason over them.”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”

   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 drawn
   Kick—none0/10

   There's no evidence of an interactive API reference or runnable code examples; probes explicitly show no OpenAPI/Swagger spec exists (all candidate paths 404), and the only 'API-like' surface is GitBook's generic docs-search MCP endpoint, which serves documentation text, not a runnable API reference.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   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 drawn
   Kick—none0/10

   A direct probe for an OpenAPI/Swagger spec returned 404 on all candidate paths, and no evidence pack item shows a downloadable machine-readable API spec for Kick's own product API; the only machine-readable surfaces found (llms.txt, GitBook MCP) serve documentation, not an API contract.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   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 drawn
   Kick—none0/10

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

   ⚑ flag

   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 drawn
   Kick—none0/10

   No evidence of a public, versioned Kick API exists — the openapi/swagger probe returned 404 on all candidate paths, and the only MCP/API-like surface found is GitBook's generic docs-search MCP endpoint, not a Kick-built account/ledger API. There is no mention anywhere in the docs of API versioning schemes or a deprecation policy.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”

   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 to Mercury Books
   Kick~partialclaimed5/10

   Kick's AI categorizes ~97% of transactions automatically and rules apply logic across every matching transaction going forward, and multi-entity transaction splitting affects many items at once — all forms of bulk-scale automation. However there is no documented bulk-edit UI, batch API, or CLI/MCP action surface for an AI agent to programmatically trigger bulk operations across many items on demand. Missing for 10: explicit bulk-select/bulk-edit feature, a programmatic bulk-action API or CLI, and evidence of agent-triggered bulk operations beyond passive AI categorization.

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”
   • [claimed-docs] “For expenses shared across businesses - like rent, software, or insurance - you can split a single transaction across multiple entities by a…”
   • [claimed-docs] “Upload PDF bank statements or CSVs for institutions not supported by Plaid, or to backfill historical data.”

   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 Kick
   Kick~partialclaimed6/10

   Kick's documented Rules feature lets users define logic that overrides AI categorization and 'run automatically whenever a matching transaction syncs' — a real event-triggered automation rule engine. However, this is scoped narrowly to transaction categorization events rather than a general-purpose trigger/action framework spanning arbitrary events (e.g., invoicing, bill pay, entity actions). Missing for 10: evidence of rules triggering on non-categorization events, multi-step or cross-feature actions, and any user-facing rule builder UI/API details beyond the single doc description.

   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”

   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
   Kick—none0/10

   Kick documents event-driven automation (AI categorization on sync, rules triggered by matching transactions) but no evidence of user-schedulable recurring jobs/workflows (e.g., recurring invoices, scheduled reports, cron-like automation) that an AI-native user could set up and manage.

   ⚑ 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
   Kick—none0/10

   Kick documents an audit trail (Activity tab) that logs categorization/rule changes, but there is no evidence of versioning automation Rules or rolling back an automation to a prior state — only a log of what happened, not a way to view/restore prior rule versions.

   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”

   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 drawn
   Kick~partialprobed5/10

   Kick's AI auto-categorizes ~97% of transactions and gates low-confidence items for manual review, and the product includes month-end period locks and a full audit trail logging AI agent actions — echoing pieces of an end-to-end reconciliation workflow. However, the reconciliation docs themselves describe reconciliation as a process of comparing Kick's records to bank statements without documenting that Kick's AI actually performs the matching/flagging of reconciliation exceptions (as opposed to categorization); there's no evidence of a single agent command that walks through match, flag, and prepare-for-review end-to-end. Missing for 10: documented AI-driven bank-statement matching/exception flagging specific to reconciliation (not just categorization), and a described single-agent workflow that completes a full month-end close autonomously.

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.kick.co/llms.txt # Kick Docs ## Business Owners - [Kick Docs for Business Owners](https://docs.ki…”

   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 to Mercury Books
   Kick✓fullclaimed7/10

   Kick's docs confirm bank/credit-card connection via Plaid with automatic transaction sync ('every transaction in Kick comes from a bank feed or an import'), AI categorization triggered 'when transactions sync into Kick', and a PDF/CSV fallback for institutions Plaid doesn't cover. This clearly delivers the core capability, though the exact 'daily' cadence isn't explicitly stated and there's no independent/hands-on corroboration of sync reliability. Missing for 10: explicit statement of daily sync frequency, independent verification of import reliability.

   • [claimed-docs] “"All data transmitted to and from Kick is encrypted in transit using TLS. Data at rest is encrypted using AES-256... Kick connects to your f…”
   • [claimed-docs] “Upload PDF bank statements or CSVs for institutions not supported by Plaid, or to backfill historical data.”
   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”

   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 drawn
   Kick✓fullclaimed8/10

   Kick's docs explicitly state AI auto-categorizes ~97% of transactions on first pass, learns from user corrections, and lets users create Rules that override AI categorization permanently for future matching transactions — directly matching the story's requirement for learning-based categorization suggestions. Confidence gating (low-confidence transactions left uncategorized) further supports a learning/feedback loop. Missing for 10: no independent/hands-on verification of the learning accuracy or how quickly corrections propagate, and no detail on the mechanism (per-vendor vs. global learning).

   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”

   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 to Kick
   Kick~partialclaimed6/10

   Kick's docs describe reconciliation as comparing ledger transactions against bank/credit statements to confirm amounts, dates, and flag missing or duplicate transactions, which aligns with the matched/unmatched/duplicate framing in the story. However, there's no detailed evidence of a dedicated UI that explicitly buckets transactions into 'matched,' 'unmatched,' and 'duplicate' categories for accountant review, nor screenshots or workflow steps showing how discrepancies are resolved. Missing for 10: explicit UI/workflow evidence of distinct matched/unmatched/duplicate views, reconciliation report exports, and independent/hands-on confirmation of the review process.

   • [claimed-docs] “Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythin…”
   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”

   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 drawn
   Kick~partialclaimed3/10

   Kick can 'view and manage' bills synced in real time from Ramp or BILL, but the docs explicitly note Kick does not capture bills natively or execute vendor payments itself — it relies on synced data from external AP tools, and there is no documented approval-routing workflow within Kick. Missing for 10: native bill capture/OCR intake, an in-app approval-routing step, and evidence of Kick itself scheduling/executing payments (currently pass-through from Ramp/BILL).

   • [claimed-docs] “View and manage your bills in Kick, with real-time sync from Ramp or BILL.”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”

   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 Kick
   Kick~partialclaimed4/10

   Kick supports AP-adjacent features — viewing and managing bills with real-time sync from Ramp/BILL (kick-docs-13, kick-supp-invoicing-billpay), a real double-entry ledger (kick-supp-journal-entries), and locked periods that keep historical reports stable so numbers can be trusted 'at any point in time' (kick-supp-locks, kick-docs-14). However, there is no explicit documentation of an AP aging report (e.g., 30/60/90-day buckets) or a vendor-balance summary view — only bill list/sync visibility is evidenced. Missing for 10: dedicated AP aging report, vendor balance summary/report, and evidence of historical point-in-time AP snapshots beyond generic locked-period stability.

   • [claimed-docs] “View and manage your bills in Kick, with real-time sync from Ramp or BILL.”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”
   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “Reports for locked periods remain accurate and stable.”

   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 to Kick
   Kick✓fullclaimed9/10

   Kick documents explicit period locking: an accountant locks a period after review, which 'protects the finalized books for that period from being changed - by anyone, including you,' and locked-period reports 'remain accurate and stable,' implying reopening is required for changes. This directly matches the accountant story of preventing prior-period edits without explicit reopening. Missing for 10: explicit documentation of the reopening workflow/permissions and independent/hands-on confirmation beyond vendor docs.

   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “Reports for locked periods remain accurate and stable.”

   proof ↗⚑ 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 Kick
   Kick~partialclaimed5/10

   Kick documents core close primitives — reconciliation against bank statements, period locks that finalize books, an audit trail of activity/AI actions, and rules/categorization workflows — which together support month-end close discipline. However, there is no evidence of a dedicated checklist feature tracking accruals as discrete tasks, formal review sign-off workflows, or a consolidated close-status dashboard for accountants. Missing for 10: a documented month-end checklist UI, explicit accrual task tracking, and formal sign-off/approval steps beyond simple period locking.

   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [claimed-docs] “Rules let you tell Kick exactly how to handle specific transactions - overriding AI categorization with your own logic.”
   • [claimed-docs] “"Kick sets up a standard Chart of Accounts when you create your workspace, and you or your accountant can adjust it from there: adding, rena…”

   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 drawn
   Kick✓fullclaimed8/10

   Kick explicitly supports role-based access control ('you decide exactly who can see and do what'), lock periods where an accountant can finalize and lock books against changes, a full audit trail of workspace activity, and a dedicated Tax Package/accountant workflow with a marketed accountants page — together enabling a founder to invite an external accountant with scoped access to review/adjust books. Missing for 10: no explicit documentation of granular invite flow or specific role types (e.g., 'accountant' vs 'bookkeeper' role names) and no independent/hands-on confirmation of the invite UX.

   • [claimed-docs] “Kick uses role-based access control so you decide exactly who can see and do what in your workspace.”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [claimed-docs] “The Tax Package generates a single Excel file with everything your accountant or tax preparer needs to file your taxes - no manual exports, …”
   • [claimed-docs] “We pivoted off QBO completely, and our team now outputs 10x what we used to without adding a single headcount.”
   • [claimed-docs] “Reports for locked periods remain accurate and stable.”

   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 drawn
   Kick—none0/10

   Kick documents a real double-entry ledger, chart of accounts, and journal entries, but there is no evidence of a documented API for exporting the general ledger or trial balance in open formats — the openapi probe returned 404s on all candidate endpoints, and the only 'API'-like surfaces found are a GitBook docs-search MCP server and Google Sheets AI integration, neither of which expose ledger/GL data programmatically.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [claimed-docs] “"Kick sets up a standard Chart of Accounts when you create your workspace, and you or your accountant can adjust it from there: adding, rena…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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
   Kick✓fullclaimed8/10

   Kick connects banking via Plaid (with manual PDF/CSV backfill for unsupported institutions), syncs payment/invoicing data from Stripe, Mercury, Ramp, and BILL, and posts payroll runs directly as journal entries into a real double-entry ledger with automated AI categorization. missing for 10: explicit named payroll provider integrations (e.g., Gusto/Rippling) beyond the generic 'payroll run' mention, and independent third-party corroboration beyond Kick's own docs.

   • [claimed-docs] “Upload PDF bank statements or CSVs for institutions not supported by Plaid, or to backfill historical data.”
   • [claimed-docs] “View invoices synced from Stripe, Mercury, and BILL, and create and send invoices directly from Kick.”
   • [claimed-docs] “View and manage your bills in Kick, with real-time sync from Ramp or BILL.”
   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”

   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 Kick
   Kick~partialclaimed5/10

   Kick documents CSV/PDF backfill for historical data and offers a paid 'Advanced' tier with dedicated 'migration support,' plus a customer testimonial about switching off QBO — suggesting migration is a supported workflow. However, there's no documentation of how transaction-level detail, historical journal entries, or opening balances are preserved during a full accounting-system migration. Missing for 10: detailed migration/import methodology, evidence of transaction-level fidelity (e.g., historical journal entries, categorization history) surviving migration, and independent corroboration beyond one testimonial.

   • [claimed-docs] “Upload PDF bank statements or CSVs for institutions not supported by Plaid, or to backfill historical data.”
   • [claimed-docs] “We pivoted off QBO completely, and our team now outputs 10x what we used to without adding a single headcount.”
   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”

   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 Kick
   Kick~partialclaimed5/10

   Kick lets founders create and send invoices directly and also view invoices synced from Stripe, Mercury, and BILL, giving AR visibility; but the docs describe invoicing as largely a sync/view layer for AR (no native online payment collection is documented, and there's no mention of payment-status tracking like 'viewed' or 'paid' timestamps within Kick itself — that likely happens on the connected platform, not in Kick). missing for 10: documented online payment collection built into Kick-issued invoices, and explicit view/paid status tracking or notifications within Kick's own invoicing UI.

   • [claimed-docs] “View invoices synced from Stripe, Mercury, and BILL, and create and send invoices directly from Kick.”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”

   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 drawn
   Kick—none0/10

   Kick's docs confirm basic invoicing (viewing synced invoices from Stripe/Mercury/BILL, and creating/sending invoices directly from Kick) but there is no mention anywhere in the evidence of recurring/repeating invoice schedules or automated overdue-payment reminders. missing for 10: recurring invoice scheduling, automatic overdue payment reminder/dunning workflow.

   • [claimed-docs] “View invoices synced from Stripe, Mercury, and BILL, and create and send invoices directly from Kick.”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”

   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 Kick
   Kick~partialclaimed5/10

   Kick supports AR via invoices synced from Stripe/Mercury/BILL and native invoice creation (kick-docs-12, kick-supp-invoicing-billpay), and the Plus plan advertises 'AR & AP' as a feature (kick-supp-pricing), implying some balance tracking exists. However, there is no documented aging report, no explicit per-customer balance/statement view, and AR appears to depend on synced platforms rather than a dedicated native AR module. Missing for 10: documented aging reports (30/60/90-day buckets), per-customer balance ledger or statement view, and any hands-on/independent confirmation of AR reporting depth.

   • [claimed-docs] “View invoices synced from Stripe, Mercury, and BILL, and create and send invoices directly from Kick.”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”
   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”

   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 drawn
   Kick—none0/10

   Kick documents journal entries, categorization confidence-gating, rules, and period locks, but there is no evidence of a public API/SDK for agents to draft or post journal entries programmatically, nor any 'review queue' workflow exposed via API. The only discovered API-like surface is a GitBook docs-search MCP endpoint (docs only, not ledger actions), and explicit probes for an OpenAPI spec returned 404s.

   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”

   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 Kick
   Kick~partialclaimed6/10

   Docs confirm a standard Chart of Accounts that accountants can add/rename/restructure, and pricing explicitly lists 'classes' as a Plus-tier dimension feature, supporting class-based tagging. However there is no explicit documentation of sub-account/parent-child hierarchies or generic 'tag' dimensions beyond classes, and account-type customization is only implied by 'restructuring' rather than detailed. Missing for 10: explicit sub-account nesting support, explicit account-type editing controls, and tag (non-class) dimension documentation.

   • [claimed-docs] “"Kick sets up a standard Chart of Accounts when you create your workspace, and you or your accountant can adjust it from there: adding, rena…”
   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”

   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 drawn
   Kick~partialclaimed5/10

   Kick documents a genuine double-entry ledger where every transaction generates a journal entry with debit/credit sides, plus a chart of accounts accountants can adjust, supporting the underlying ledger mechanics. However, the evidence describes journal entries as system-generated from transactions/payroll/bills, not explicit manual entry creation by an accountant with supporting memos. Missing for 10: explicit documentation of manually creating/posting a journal entry, memo/description fields on manual entries, and confirmation entries must balance before posting.

   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [claimed-docs] “"Kick sets up a standard Chart of Accounts when you create your workspace, and you or your accountant can adjust it from there: adding, rena…”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”

   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 Kick
   Kick~partialclaimed5/10

   Kick's reconciliation workflow explicitly checks for missing/duplicate transactions before close, and AI categorization has confidence-gating that flags low-confidence transactions for manual review, with all actions logged in a full audit trail — covering pieces of anomaly detection. However, there's no documented feature where an agent proactively/continuously monitors the ledger and surfaces anomaly or duplicate alerts ahead of close; the AI-agent angle is limited to external LLMs reasoning over exported Sheets report data, not a native monitoring agent. Missing for 10: a dedicated automated agent/alerting workflow for anomaly and duplicate detection tied to close, and evidence of proactive (vs. manual/scheduled) flagging.

   • [claimed-docs] “"Reconciliation is the process of comparing your transactions in Kick against your actual bank or credit card statements to confirm everythi…”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [claimed-docs] “Your Kick reports land as live spreadsheet data in your workbook, so Gemini, Claude, or ChatGPT can read and reason over them.”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”

   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 to Kick
   Kick✓fullclaimed8/10

   Kick documents a full Activity tab audit trail logging every transaction change, categorization update, and sync event with timestamp and actor (including AI agent actions), plus period locks that prevent retroactive changes to closed periods and RBAC to control who can act. This directly covers who-changed-what-when across the ledger, including multi-entity workspaces. Missing for 10: no independent/hands-on corroboration of the audit trail in practice, no detail on exporting/filtering audit logs for compliance review, and no explicit confirmation the trail spans across all entities in a multi-entity workspace simultaneously.

   • [claimed-docs] “"The Activity tab is a full audit trail of everything that's happened in your workspace. Every transaction change, categorization update, an…”
   • [claimed-docs] “The Activity tab is a full audit trail of everything that's happened in your workspace.”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “Reports for locked periods remain accurate and stable.”
   • [claimed-docs] “Kick uses role-based access control so you decide exactly who can see and do what in your workspace.”
   • [claimed-docs] “If you own more than one business, or have a holding company structure, Kick lets you manage all your entities from a single workspace.”

   proof ↗⚑ 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 to Kick
   Kick~partialclaimed5/10

   Kick documents multi-entity management from a single workspace, including cross-entity expense splitting (kick-docs-5, kick-docs-6), and pricing tiers explicitly support 'unlimited entities' (kick-supp-pricing). However, there is no explicit documentation of consolidated financial statements or roll-up reporting across entities—only per-entity management and transaction splitting are described. Missing for 10: explicit consolidated P&L/Balance Sheet reporting across entities, evidence of a consolidation feature or combined financial statement output.

   • [claimed-docs] “If you own more than one business, or have a holding company structure, Kick lets you manage all your entities from a single workspace.”
   • [claimed-docs] “For expenses shared across businesses - like rent, software, or insurance - you can split a single transaction across multiple entities by a…”
   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”

   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 drawn
   Kick—none0/10

   Evidence shows no general Kick API: OpenAPI/swagger probes all 404'd, the only MCP endpoint found is a GitBook docs-search server explicitly noted to serve documentation, not Kick account data or ledger actions, and the AI workflow route is one-directional Google Sheets report export (with limited spreadsheet write-back, not writing into Kick). There is no evidence of programmatic access to core UI actions like categorization, reconciliation, invoicing, or entity management.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [claimed-docs] “AR and AP run through integrations plus native invoicing: "View invoices synced from Stripe, Mercury, and BILL, and create and send invoices…”

   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 Kick
   Kick~partialclaimed3/10

   Kick offers some export surfaces — a Tax Package that bundles reports into a single Excel file and live Google Sheets sync of reports for AI tools to read — but there is no documented capability to export the full ledger/transactions/journal entries in bulk open formats (CSV/JSON) or a documented account-closure/migration export process; 'migration support' is only mentioned as a paid Advanced-tier perk with no detail. missing for 10: full-data export (transactions, journal entries, chart of accounts) in open formats, documented account closure/migration workflow, evidence of independent/hands-on export testing.

   • [claimed-docs] “The Tax Package generates a single Excel file with everything your accountant or tax preparer needs to file your taxes - no manual exports, …”
   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”
   • [claimed-docs] “Upload PDF bank statements or CSVs for institutions not supported by Plaid, or to backfill historical data.”

   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
   Kick—none0/10

   Kick's evidence pack (security, pricing, integrations, multi-entity docs) never mentions data residency options, regional storage selection, or geographic data controls; only generic encryption-in-transit/at-rest claims are documented.

   • [claimed-docs] “"All data transmitted to and from Kick is encrypted in transit using TLS. Data at rest is encrypted using AES-256... Kick connects to your f…”

   proof ↗⚑ 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 userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Kick—none0/10

   Kick's evidence covers security (encryption, RBAC, audit trail) and AI-based categorization, but there is no documentation of an opt-out for AI/model training on user data, no privacy policy excerpt, and no data-usage/training statement of any kind.

   ⚑ flag

   Mercury Books—none0/10

   The evidence pack contains no mention of data-training opt-outs, AI model training policies, or privacy controls specific to preventing customer data from being used to train AI models; Mercury Books' AI features (Command) are described functionally but with no privacy-posture documentation on this axis. Missing for 10: any privacy policy language, opt-out mechanism, or documentation addressing whether user financial data is used to train AI models.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Kick—none0/10

   The evidence covers encryption, RBAC, and audit trails but contains no mention of data retention policies, data export, or account/data deletion controls that a user could invoke. Nothing addresses this axis at all, so it applies but is unaddressed.

   ⚑ 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

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

   weight 2 · round drawn
   Kick—none0/10

   Kick is an accounting/bookkeeping SaaS product, and no evidence pack item addresses telemetry/usage-tracking opt-out settings, a privacy control panel, or any documented data-collection preferences for the product itself. The security doc only covers encryption and Plaid credential handling, not telemetry opt-out.

   ⚑ flag

   Mercury Books—none0/10

   No evidence anywhere in the pack mentions telemetry, usage tracking, data collection settings, or opt-out controls; the material focuses entirely on accounting features, AI assistant capabilities, and pricing. This is a fair privacy-posture question for any SaaS product, so absence of evidence yields 'none' rather than 'na'.

   ⚑ 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 Kick
   Kick~partialprobed4/10

   Kick documents an AI workflow where live report data lands in Google Sheets so Gemini/Claude/ChatGPT can read and reason over it, which could support a question like "can we afford X?", but this runs through a spreadsheet bridge, not a genuine public ledger API — probes show openapi/swagger endpoints all 404, and the only live MCP endpoint found serves GitBook documentation search, not ledger data or account actions. Missing for 10: a documented public API or account-scoped MCP server exposing live ledger data directly to agents, and any evidence of natural-language affordability Q&A being answered from it.

   • [claimed-docs] “The documented AI workflow routes through Google Sheets: "Use Gemini, Claude, or ChatGPT on live Kick report data in Google Sheets... Your K…”
   • [claimed-docs] “Your Kick reports land as live spreadsheet data in your workbook, so Gemini, Claude, or ChatGPT can read and reason over them.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.kick.co/openapi.json, https://docs.kick.co/swagger.json, https://docs.kick.co/api/opena…”
   • [probe] “PROBE mcp-docs (2026-09-16): keyless JSON-RPC initialize to https://docs.kick.co/~gitbook/mcp completes a real MCP handshake (HTTP 200, prot…”
   • [claimed-docs] “The docs are agent-legible via GitBook: a full llms.txt index, .md markdown mirrors on every page, and a documented dynamic query interface …”

   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 drawn
   Kick—none0/10

   Evidence only shows that the Plus plan includes 'classes' as a feature label in pricing (kick-supp-pricing), but there is no documentation of a report builder that lets users filter/group by class, location, or tag dimensions, nor any mention of 'location' or 'tag' dimensions at all. Missing for 10: documented custom report builder UI, filter/group-by controls, evidence of location dimension, evidence of tag dimension.

   • [claimed-docs] “Published plan table: "Free — $0/mo — 1 entity, up to 250 transactions/year, core features; Basic — $40/mo — 1 entity, unlimited transaction…”

   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 to Mercury Books
   Kick~partialclaimed6/10

   Kick's docs show a real double-entry ledger with live P&L and Balance Sheet organized by Chart of Accounts, updating in real time as transactions are categorized, plus period locking that keeps historical reports accurate for any locked period (kick-supp-coa, kick-supp-categorization, kick-supp-journal-entries, kick-supp-locks). However, no evidence explicitly confirms a cash-flow statement report or an 'any period on demand' report generator UI — missing for 10: explicit cash-flow statement documentation, evidence of arbitrary custom date-range reporting on demand, and independent/hands-on verification of statement accuracy.

   • [claimed-docs] “"Kick sets up a standard Chart of Accounts when you create your workspace, and you or your accountant can adjust it from there: adding, rena…”
   • [claimed-docs] “"Kick automatically categorizes your transactions and learns from your changes. When transactions sync into Kick, the AI categorizes approxi…”
   • [claimed-docs] “Kick is a real double-entry ledger: "Every transaction in Kick - whether it came from your bank, a payroll run, or a bill - generates a jour…”
   • [claimed-docs] “Period locking is documented: "When your accountant finishes reviewing and closing a period, they lock it. A lock protects the finalized boo…”
   • [claimed-docs] “The Tax Package generates a single Excel file with everything your accountant or tax preparer needs to file your taxes - no manual exports, …”

   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