Puzzle vs Digits

Agent access

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

   weight 2 · round to Digits
   Puzzle✓fullprobed8/10

   A live probe confirms Puzzle's help center serves a valid llms.txt file at help.puzzle.io/llms.txt (HTTP 200) with structured markdown links to docs, directly satisfying the ability to point an agent at agent-oriented docs. Missing for 10: independent/community confirmation of agents successfully consuming this file, and broader agent-doc formats (e.g., per-page .md mirrors, which probes show 404).

   • [probe] “PROBE llms.txt: HTTP 200 at https://help.puzzle.io/llms.txt # Puzzle Help Center > Help center for Puzzle ## Puzzle Overview - [Quick Sta…”
   • [probe] “PROBE docs-md: HTTP 404 at https://help.puzzle.io/en/.md”

   proof ↗⚑ flag

   Digits✓fullprobed9/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle—none0/10

   Puzzle's evidence only shows marketing language about an 'API' for embedding accounting into platforms and an MCP integration for Claude chat — neither documents headless CLI operation, CI pipeline usage, or automation-oriented tooling. No SDK, auth flow, or CI examples are present, so there's no evidence of headless/CI automation support.

   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “With Puzzle’s Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “your platform gets automated AI bookkeeping, real-time financial insights, and a clean data foundation built to scale”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits~partialprobed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Puzzle—none0/10

   Evidence shows Puzzle exposes its own MCP server so external AI clients (e.g., Claude) can pull Puzzle's financial data — the reverse of the story's ask. There is no evidence that Puzzle itself can consume or plug in external MCP servers to gain their tools.

   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”
   • [claimed-docs] “How to setup your Puzzle MCP”

   proof ↗⚑ flag

   Digits—none0/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Digits
   Puzzle✓fullclaimed7/10

   Puzzle documents an official MCP server integration that connects Puzzle accounts to Claude for natural-language access to financial data, with a dedicated setup guide (puzzle-docs-2, puzzle-docs-22, puzzle-docs-33). This is a first-party, product-level MCP server offering, fitting the axis for a non-agent SaaS product. Missing for 10: independent/hands-on confirmation that the MCP server works as documented, and technical details on supported tool calls/scopes.

   • [claimed-docs] “How to setup your Puzzle MCP”
   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”

   proof ↗⚑ flag

   Digits✓fullprobed9/10

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

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

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Puzzle—none0/10

   Puzzle's evidence pack documents an API, an MCP integration, and various in-app AI features, but there is no mention of an official CLI tool anywhere in the docs or probes. Missing for 10: any CLI documentation, CLI installation instructions, or CLI command reference.

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

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

   weight 3 · round to Digits
   Puzzle~partialprobed4/10

   Puzzle markets an 'Embedded Accounting' API and has a help article on 'API Access in Puzzle' describing platform-to-platform integration intent, suggesting a documented public API exists. However, probes for actual API reference material (OpenAPI/swagger specs, docs-md) returned 404s, and no evidence pack item shows endpoint-level documentation, auth flow, or SDKs. Missing for 10: a public API reference/spec, authentication and endpoint documentation, and independent confirmation that AI-native users can programmatically drive the product via this API.

   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “With Puzzle’s Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits✓fullprobed9/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle—none0/10

   Evidence shows Puzzle has an API and MCP integration for connecting agents (e.g., Claude) to account data, but there is no mention of issuing scoped, least-privilege API credentials, permission scopes, or granular token controls for agents. missing for 10: scoped API key/token generation, permission/role-based credential scoping, documentation of least-privilege access controls for agent integrations.

   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”

   proof ↗⚑ flag

   Digits~partialprobed6/10

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

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

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Puzzle~partialprobed5/10

   Puzzle offers a documented API for embedded accounting and an MCP integration for Claude, showing some official developer surfaces, but there's no evidence of a formal SDK (client libraries, language bindings) or OpenAPI spec — probes for openapi.json all returned 404. missing for 10: official SDK/client libraries in specific languages, published OpenAPI/API reference spec, independent developer corroboration of building against the API.

   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “With Puzzle’s Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits~partialprobed5/10

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

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

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to Digits
   Puzzle—none0/10

   No evidence of webhook subscription capability anywhere in the pack; Puzzle offers an API and MCP integration for querying data, but nothing about event-driven webhooks.

   ⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round drawn
   Puzzle✓fullclaimed8/10

   Puzzle offers a conversational 'ask anything' insights feature (cash trending, profitability, fundraising readiness) plus AI Close agents that surface discrepancies, AI-driven categorization suggestions, and MCP integration for natural-language querying of financial data via Claude — all directly delivering AI-generated insights/suggestions from the user's own data. Missing for 10: independent hands-on verification of insight accuracy/quality beyond marketing copy and only one general community mention unrelated to this specific feature.

   • [claimed-docs] “Ask anything about your business, instantly, in plain English. "How's my cash trending?" "Am I ready to raise?" "Which months am I actually …”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “A user can click on a button and “ask AI” for help in categorizing a transaction —without context switching between tools.”
   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Hand off the busywork. Finding software subscriptions, matching invoices to payments, pulling together what your accountant needs — describe…”

   proof ↗⚑ flag

   Digits✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle~partialclaimed6/10

   Puzzle documents concrete background automations — 'AI Close' agents that autonomously reconcile accounts, review transactions and surface discrepancies during month-end, plus custom categorization rules and batch auto-categorization (up to 98%) that run without manual triggering. However these are fixed, accounting-specific automations rather than a general-purpose 'set up your own automation' framework, and there's no independent/hands-on evidence confirming reliability of unattended runs. Missing for 10: user-configurable triggers/schedules for arbitrary automations, evidence of true autonomy without review gates, and independent verification of background execution.

   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Creating custom rules”
   • [claimed-docs] “Batch Categorize Transactions”
   • [claimed-docs] “Up to 98% auto-categorization”

   proof ↗⚑ flag

   Digits~partialclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Puzzle
   Puzzle✓fullclaimed8/10

   Puzzle ships built-in AI features (AI Close, Accounting AI) described as using 'AI agents to reconcile accounts, review transactions, and surface discrepancies,' plus an 'Ask AI' button for categorization help and natural-language financial queries — all within the product itself, not an external agent. Missing for 10: independent/hands-on verification of these AI features actually completing delegated tasks, and clearer detail on autonomy vs human-review boundaries.

   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “A user can click on a button and “ask AI” for help in categorizing a transaction —without context switching between tools.”
   • [claimed-docs] “Accounting AI runs prompts on top of your general ledger. The output reflects your existing accounts and categories.”
   • [claimed-docs] “How to import a PDF or CSV using Accounting AI”
   • [claimed-docs] “Ask anything about your business, instantly, in plain English. "How's my cash trending?" "Am I ready to raise?" "Which months am I actually …”
   • [claimed-docs] “Hand off the busywork. Finding software subscriptions, matching invoices to payments, pulling together what your accountant needs — describe…”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Puzzle✓fullclaimed7/10

   Puzzle documents natural-language interaction via its MCP integration with Claude ('instant access to your financial data through natural conversation') and multiple AI features letting users 'ask anything about your business in plain English' or 'ask AI' to categorize transactions, plus AI Close agents automating close tasks from natural prompts. Missing for 10: independent/hands-on verification that NL commands can trigger broader actions (not just queries) and third-party corroboration of the MCP/Claude workflow in practice.

   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”
   • [claimed-docs] “Ask anything about your business, instantly, in plain English. "How's my cash trending?" "Am I ready to raise?" "Which months am I actually …”
   • [claimed-docs] “A user can click on a button and “ask AI” for help in categorizing a transaction —without context switching between tools.”
   • [claimed-docs] “Accounting AI runs prompts on top of your general ledger. The output reflects your existing accounts and categories.”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”

   proof ↗⚑ flag

   Digits✓fullprobed7/10

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

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

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Digits
   Puzzle—none0/10

   Puzzle documents an API (puzzle.io/api) and an MCP integration, but there is no evidence of an interactive API reference or runnable examples; probes for OpenAPI/Swagger specs at expected paths all returned 404, suggesting no such interactive reference exists.

   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”
   • [probe] “PROBE docs-md: HTTP 404 at https://help.puzzle.io/en/.md”

   proof ↗⚑ flag

   Digits~partialprobed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle—none0/10

   Puzzle has an API and mentions API access docs, but the probe explicitly found no OpenAPI/swagger spec at any candidate path, and no evidence pack item references a downloadable machine-readable spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”

   proof ↗⚑ flag

   Digits✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Digits
   Puzzle—none0/10

   No evidence in the pack mentions a sandbox, test, or staging environment for Puzzle's API or product that would let a user test without touching production financial data; only production-focused API and bookkeeping features are documented.

   ⚑ flag

   Digits✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle—none0/10

   The evidence pack shows Puzzle has an API and MCP integration (puzzle-docs-42, puzzle-docs-21) but contains no mention of API versioning scheme or a documented deprecation policy; probes for OpenAPI specs all returned 404. Missing for 10: any versioning scheme documentation, changelog, or deprecation/sunset policy.

   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [claimed-docs] “With Puzzle’s Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Puzzle~partialclaimed6/10

   Puzzle documents concrete bulk-operation features—batch categorizing transactions, bulk CSV import of manual journal entries, and bulk CSV upload of the Chart of Accounts—plus rule-based automation for categorization, all first-party docs. However, these bulk mechanisms are CSV/rule-based rather than explicitly exposed through the AI/API/MCP layer for an 'AI-native' agent to invoke programmatically at scale. Missing for 10: explicit evidence that the API or MCP integration itself supports issuing bulk operations (not just UI/CSV uploads), and independent/hands-on confirmation of bulk-op reliability at scale.

   • [claimed-docs] “Batch Categorize Transactions”
   • [claimed-docs] “Need to post more than one manual journal entry at a time? Instead of adding them one by one, you can upload a batch of entries all at once …”
   • [claimed-docs] “If you need to bulk add or edit your Chart of Accounts in Puzzle, you can do so by uploading a CSV file directly from your Company Settings.”
   • [claimed-docs] “Creating custom rules”
   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Puzzle
   Puzzle~partialclaimed5/10

   Puzzle documents 'Creating custom rules' for transaction categorization, letting users define rules that automatically trigger categorization when transactions occur, and AI Close agents that automate reconciliation on close events — concrete evidence of rule-based automation tied to events. However, this is scoped narrowly to bookkeeping categorization/close workflows rather than a general-purpose rules engine spanning arbitrary triggers and actions. Missing for 10: evidence of a broader, user-configurable trigger-action framework beyond categorization/close (e.g., custom webhooks, conditional workflows across modules), and independent confirmation of rule behavior in practice.

   • [claimed-docs] “Creating custom rules”
   • [claimed-docs] “Batch Categorize Transactions”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”

   proof ↗⚑ flag

   Digits~partialclaimed3/10

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

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

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Puzzle—none0/10

   Puzzle documents AI-driven automation for close, categorization, and reconciliation, but there is no evidence of any capability to schedule recurring jobs or workflows (e.g., recurring invoices, scheduled reports, or timed automation triggers).

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

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

   weight 1 · round drawn
   Puzzle—none0/10

   Puzzle documents automation features (custom categorization rules, AI Close, batch categorization) but no evidence describes versioning, reviewing, or rolling back these automations themselves — the only 'rollback' mentioned is voiding a manual journal entry, not an automation rule change. Missing for 10: version history for rules/automations, review/approval workflow for automation changes, and a documented rollback mechanism for automations.

   • [claimed-docs] “Creating custom rules”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Puzzle automatically creates a voiding (reversing) journal entry for the original and posts a new entry reflecting your changes”

   proof ↗⚑ flag

   Digits—none0/10

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

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

   proof ↗⚑ flag

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
   Puzzle~partialclaimed6/10

   Puzzle's AI Close feature explicitly uses AI agents to reconcile accounts, review transactions, and surface discrepancies for month-end close, directly matching the story's core ask (puzzle-docs-24, puzzle-docs-39, puzzle-docs-5). However, evidence doesn't confirm full end-to-end autonomy or explicit 'preparation for human review' handoff workflow beyond general review-before-final claims, and there's no independent/hands-on validation of the AI Close agent's reconciliation accuracy or exception-flagging in practice. missing for 10: independent/hands-on verification of AI Close performance, detailed documentation of exception-flagging logic, explicit human-review handoff/approval workflow, and evidence of full end-to-end (not just partial/batch) reconciliation coverage.

   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Month-End close with AI Close”
   • [claimed-docs] “Hand off the busywork. Finding software subscriptions, matching invoices to payments, pulling together what your accountant needs — describe…”
   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Bank feeds

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

   weight 3 · round to Digits
   Puzzle✓fullclaimed7/10

   Puzzle's docs describe connecting bank/credit-card accounts and third-party sources (Brex, Ramp, Stripe) with automated categorization (98% categorized) and reconciliation workflows, which directly supports the daily-import banking-reconciliation story (puzzle-docs-29, -15, -14, -13, -18, -19). However, there's no explicit statement about daily import cadence or independent verification of reliability. Missing for 10: explicit 'daily auto-sync' language, third-party/hands-on confirmation of import frequency and accuracy.

   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”
   • [claimed-docs] “98% transactions categorized When you connect Brex with Puzzle”
   • [claimed-docs] “2x faster to close books When you connect Ramp with Puzzle”
   • [claimed-docs] “3 min to reconcile revenue When you connect Stripe with Puzzle”
   • [claimed-docs] “Up to 98% auto-categorization”
   • [claimed-docs] “Puzzle customers who fully onboard and connect supported integrations can reduce the time required to complete their monthly close by 50% or…”

   proof ↗⚑ flag

   Digits✓fullclaimed8/10

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

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

   proof ↗⚑ flag

Categorization

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

   weight 2 · round drawn
   Puzzle~partialclaimed6/10

   Puzzle clearly ships automatic transaction categorization with high accuracy claims (up to 98%), custom rules, batch categorization, and an 'ask AI' assist button, showing an active categorization engine tied to user-configurable rules. However, there is no explicit documentation describing a feedback loop where the AI model learns from user corrections over time (as opposed to static rules the user manually creates). missing for 10: explicit description of ML/AI learning from user corrections, evidence of improved suggestion accuracy after corrections, independent confirmation of this adaptive behavior.

   • [claimed-docs] “Creating custom rules”
   • [claimed-docs] “Batch Categorize Transactions”
   • [claimed-docs] “Up to 98% auto-categorization”
   • [claimed-docs] “A user can click on a button and “ask AI” for help in categorizing a transaction —without context switching between tools.”
   • [claimed-docs] “98% transactions categorized When you connect Brex with Puzzle”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Reconciliation

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

   weight 3 · round to Puzzle
   Puzzle✓fullclaimed7/10

   Puzzle has a dedicated reconciliation feature for bank/credit card accounts explicitly designed to ensure every transaction is accounted for and matches the bank statement (puzzle-docs-29), plus AI Close automates reconciling accounts, reviewing transactions, and surfacing discrepancies (puzzle-docs-24, puzzle-docs-39). This covers the core reconcile-and-surface-for-review workflow an accountant needs. Missing for 10: explicit documentation of distinct 'matched/unmatched/duplicate' transaction states or UI surfacing terminology, and independent/hands-on validation beyond vendor docs.

   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”

   proof ↗⚑ flag

   Digits~partialclaimed5/10

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

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

   proof ↗⚑ flag

Bill management

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

   weight 2 · round to Digits
   Puzzle—none0/10

   The evidence pack covers bookkeeping, categorization, close automation, invoicing (AR), and reporting, but contains no mention of vendor bill capture, approval routing, or payment scheduling (AP workflow) anywhere in the docs or help center listings.

   ⚑ flag

   Digits~partialclaimed7/10

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

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

   proof ↗⚑ flag

Payables

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

   weight 2 · round to Digits
   Puzzle—none0/10

   The evidence pack covers bookkeeping, categorization, month-end close, invoicing (AR), reconciliation, and reporting exports, but contains no mention of accounts payable, vendor bills, bill tracking, or AP aging reports. Missing for 10: any documentation of a bills/AP module, vendor balance tracking, or an AP aging report feature.

   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “Yes, you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “Puzzle's invoice editor lets you build a professional, branded invoice and see exactly how it will look as you go!”

   proof ↗⚑ flag

   Digits~partialclaimed7/10

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

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

   proof ↗⚑ flag

Close process

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

   weight 2 · round drawn
   Puzzle—none0/10

   The evidence covers AI-assisted month-end close, reconciliation, and journal entry reversals, but nowhere mentions locking closed periods or requiring an explicit reopening step to prevent prior-period changes. This is a standard, applicable accounting-software axis, but no documentation or community evidence confirms it exists in Puzzle.

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

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

   weight 3 · round to Digits
   Puzzle~partialclaimed5/10

   Puzzle's 'AI Close' explicitly automates month-end close by reconciling accounts, reviewing transactions, and surfacing discrepancies (puzzle-docs-24/39), and separate reconciliation docs describe matching bank/credit card transactions (puzzle-docs-29). Cash and accrual accounting are supported (puzzle-docs-20), but there's no evidence of a structured checklist UI, accrual-specific tasks, or multi-person review/sign-off workflow tracking. Missing for 10: explicit checklist/task-list feature, accrual entry tracking, and reviewer sign-off/approval workflow evidence.

   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”
   • [claimed-docs] “Cash **_and_** accrual accounting”
   • [claimed-docs] “Month-End close with AI Close”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Collaboration

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

   weight 3 · round to Digits
   Puzzle—none0/10

   Puzzle markets an accountant-facing page (migration, real-time reports, startup metrics) but no evidence describes actual user invitation, permission levels, or role-scoped access controls for external collaborators. Missing for 10: explicit invite flow, role/permission settings, and any documentation of accountant-specific access restrictions.

   • [claimed-docs] “Migrate from QuickBooks without lifting a finger or losing your client's data”
   • [claimed-docs] “Instantly see startup metrics like ARR, burn, & runway”
   • [claimed-docs] “Get real-time financial reports with one click”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Data access

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

   weight 3 · round to Digits
   Puzzle~partialprobed4/10

   Puzzle documents that users can export a full general ledger and financial statements (cash or accrual) in Excel, CSV, and PDF (open formats), and separately references an API 'architected for deep platform-to-platform integrations,' but no evidence ties GL/trial-balance export specifically to the documented API — exports appear to be a UI feature, and probes for OpenAPI/API docs (openapi.json, swagger.json) all returned 404, suggesting no publicly discoverable API reference. Missing for 10: explicit API endpoint/documentation for pulling GL and trial balance, confirmation of trial balance as a report type, and a working/discoverable OpenAPI spec.

   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats”
   • [claimed-docs] “Yes, you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits~partialprobed6/10

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

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

   proof ↗⚑ flag

Integrations

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

   weight 2 · round to Digits
   Puzzle~partialclaimed6/10

   Puzzle documents direct connections to banking/payment platforms like Stripe, Ramp, and Brex with concrete automation stats (transaction categorization, faster close, revenue reconciliation) and general bank/credit card reconciliation flows, showing banking and payments activity flows into the ledger automatically. However, no evidence names a payroll system integration (e.g., Gusto, Rippling) or shows payroll data flowing into the ledger. Missing for 10: explicit payroll system integrations, independent/hands-on confirmation of banking+payroll auto-sync working end-to-end.

   • [claimed-docs] “3 min to reconcile revenue When you connect Stripe with Puzzle”
   • [claimed-docs] “2x faster to close books When you connect Ramp with Puzzle”
   • [claimed-docs] “98% transactions categorized When you connect Brex with Puzzle”
   • [claimed-docs] “Is my revenue automatically ASC 606 compliant in Puzzle?”
   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”

   proof ↗⚑ flag

   Digits✓fullclaimed8/10

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

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

   proof ↗⚑ flag

Migration

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

   weight 1 · round to Puzzle
   Puzzle✓fullclaimed6/10

   Puzzle explicitly markets QuickBooks migration ('Migrate from QuickBooks without lifting a finger or losing your client's data', 'Switch in minutes. Free migration.'), directly addressing historical books migration without data loss for founders switching accounting systems. Missing for 10: independent/hands-on verification of transaction-level fidelity during migration, detail on which source systems beyond QuickBooks are supported, and documented handling of complex historical data edge cases (multi-entity, custom categories).

   • [claimed-docs] “Migrate from QuickBooks without lifting a finger or losing your client's data”
   • [claimed-docs] “Switch in minutes. Free migration.”

   proof ↗⚑ flag

   Digits~partialclaimed4/10

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

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

   proof ↗⚑ flag

Invoicing

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

   weight 3 · round to Puzzle
   Puzzle~partialclaimed4/10

   Puzzle has a documented invoice creation/customization feature with live preview and branded PDFs/emails (puzzle-docs-28, 40, 47), but there is no evidence of built-in online payment collection or of invoice view/paid status tracking, which are core parts of this story. Missing for 10: online payment processing integration for invoices, and view/paid status notifications or dashboards.

   • [claimed-docs] “The editor opens in a split view: the form on the left, a live preview on the right that updates as you type — so you always know what your …”
   • [claimed-docs] “Puzzle's invoice editor lets you build a professional, branded invoice and see exactly how it will look as you go!”
   • [claimed-docs] “Adding your logo and brand color takes just a few steps and applies everywhere your invoice appears — the live preview, downloaded PDFs, and…”

   proof ↗⚑ flag

   Digits~partialclaimed3/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle—none0/10

   Evidence confirms Puzzle has an invoice creation/customization editor (branding, live preview) but no documentation mentions recurring/scheduled invoices or automatic overdue payment reminders. Missing for 10: any mention of recurring invoice scheduling, dunning/reminder automation, or overdue-tracking workflows.

   • [claimed-docs] “The editor opens in a split view: the form on the left, a live preview on the right that updates as you type — so you always know what your …”
   • [claimed-docs] “Puzzle's invoice editor lets you build a professional, branded invoice and see exactly how it will look as you go!”
   • [claimed-docs] “Adding your logo and brand color takes just a few steps and applies everywhere your invoice appears — the live preview, downloaded PDFs, and…”

   proof ↗⚑ flag

   Digits~partialclaimed2/10

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

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

   proof ↗⚑ flag

Receivables

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

   weight 2 · round to Digits
   Puzzle~partialclaimed3/10

   Puzzle documents invoice creation/customization (docs-28, docs-40, docs-47) and general ledger/financial statement exports (docs-26, docs-37, docs-45), which are adjacent to AR tracking, but no evidence explicitly describes an aging report or per-customer balance view. missing for 10: explicit AR aging report feature, per-customer balance/statement view, documentation tying invoicing to AR tracking workflows.

   • [claimed-docs] “The editor opens in a split view: the form on the left, a live preview on the right that updates as you type — so you always know what your …”
   • [claimed-docs] “Puzzle's invoice editor lets you build a professional, branded invoice and see exactly how it will look as you go!”
   • [claimed-docs] “Adding your logo and brand color takes just a few steps and applies everywhere your invoice appears — the live preview, downloaded PDFs, and…”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Ai ledger

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

   weight 3 · round to Digits
   Puzzle~partialclaimed4/10

   Puzzle's API supports platform-to-platform integration and journal entries can be created/edited/imported (docs-42, docs-43, docs-31/35), and AI Close uses agents to reconcile and 'review transactions' (docs-24/39), suggesting some agent-assisted, human-reviewed workflow exists. However, there is no documented API endpoint or feature specifically for an agent to draft a journal entry and place it into a distinct 'review queue' state pending accountant approval — the evidence only shows batch/manual entry creation and general AI-close reconciliation, not a draft-and-queue mechanism. Missing for 10: explicit API support for draft/pending journal entry status, a documented review-queue or approval workflow accessible to accountants, and confirmation that AI-drafted entries route through this queue rather than posting directly.

   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [claimed-docs] “Need to post more than one manual journal entry at a time? Instead of adding them one by one, you can upload a batch of entries all at once …”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Puzzle automatically creates a voiding (reversing) journal entry for the original and posts a new entry reflecting your changes.”
   • [claimed-docs] “Puzzle automatically creates a voiding (reversing) journal entry for the original and posts a new entry reflecting your changes”

   proof ↗⚑ flag

   Digits~partialclaimed5/10

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

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

   proof ↗⚑ flag

Chart of accounts

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

   weight 3 · round to Puzzle
   Puzzle~partialclaimed6/10

   Puzzle docs confirm chart-of-accounts customization via bulk CSV upload/edit and a flexible Classes dimension with unlimited groups, supporting tag/class-based segmentation. However there's no explicit evidence of configuring account types or creating sub-accounts within the CoA structure. Missing for 10: explicit sub-account hierarchy support, account-type customization details, independent/hands-on corroboration.

   • [claimed-docs] “If you need to bulk add or edit your Chart of Accounts in Puzzle, you can do so by uploading a CSV file directly from your Company Settings.”
   • [claimed-docs] “a user can create an unlimited number of Groups for Classes”

   proof ↗⚑ flag

   Digits~partialclaimed4/10

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

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

   proof ↗⚑ flag

Journal entries

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

   weight 3 · round to Puzzle
   Puzzle~partialclaimed7/10

   Puzzle explicitly supports posting manual journal entries, including bulk CSV import for multiple entries and automatic reversing entries when editing an existing entry, indicating standard double-entry JE functionality with edit history. However, there is no explicit documentation confirming enforced debit/credit balancing validation or a dedicated memo/notes field on entries. missing for 10: explicit debit=credit validation, documented memo/description field support.

   • [claimed-docs] “Puzzle automatically creates a voiding (reversing) journal entry for the original and posts a new entry reflecting your changes.”
   • [claimed-docs] “Puzzle automatically creates a voiding (reversing) journal entry for the original and posts a new entry reflecting your changes”
   • [claimed-docs] “Need to post more than one manual journal entry at a time? Instead of adding them one by one, you can upload a batch of entries all at once …”
   • [claimed-docs] “If you need to bulk add or edit your Chart of Accounts in Puzzle, you can do so by uploading a CSV file directly from your Company Settings.”

   proof ↗⚑ flag

   Digits—none0/10

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

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

   proof ↗⚑ flag

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 Puzzle
   Puzzle✓fullclaimed7/10

   Puzzle's AI Close feature explicitly uses AI agents to 'reconcile accounts, review transactions, and surface discrepancies' as part of the month-end close workflow, directly matching the anomaly-flagging story, and reconciliation docs confirm matching transactions against bank statements to catch mismatches. Missing for 10: explicit mention of duplicate-transaction detection specifically, and independent/hands-on corroboration beyond vendor docs.

   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “AI Close helps you automate and accelerate your month-end process using AI agents to reconcile accounts, review transactions, and surface di…”
   • [claimed-docs] “Month-End close with AI Close”
   • [claimed-docs] “performing a reconciliation is the best way to ensure every single transaction is accounted for and matches your bank statement exactly—givi…”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

Audit trail

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

   weight 3 · round drawn
   Puzzle—none0/10

   No evidence describes an audit trail, change log, or user-attributed history of edits across the ledger. The closest related item (docs-31/35) only shows that editing a journal entry creates a reversing entry rather than in-place edits, which is not the same as a queryable audit trail of who changed what and when.

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

Multi entity

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

   weight 2 · round to Puzzle
   Puzzle~partialclaimed5/10

   Puzzle explicitly supports managing multiple companies/entities under one login, and documents a Joiin integration specifically for 'Multi-Entity Reporting', showing entity management and a path to consolidated reporting exist. However, true consolidated financials appear to require a third-party integration (Joiin) rather than a native consolidation engine, and there's no evidence of native cross-entity elimination, intercompany accounting, or a built-in consolidated financial statement generator. Missing for 10: native consolidation/elimination features, evidence of intercompany transaction handling, and independent confirmation the Joiin integration fully satisfies audit-grade consolidated reporting.

   • [claimed-docs] “Puzzle supports managing multiple companies (entities) under one login.”
   • [claimed-docs] “Puzzle supports managing **multiple companies (entities)** under one login.”
   • [claimed-docs] “Puzzle + Joiin Integration: Multi-Entity Reporting”

   proof ↗⚑ flag

   Digits—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Digits
   Puzzle~partialprobed3/10

   Puzzle exposes an API for embedded accounting and bookkeeping data (puzzle-docs-1, puzzle-docs-42) plus CSV/journal bulk import tools, but there is no documentation claiming or demonstrating that every UI action (invoicing, reconciliation, categorization rules, AI Close workflows) is exposed via the API, and a probe for an OpenAPI/swagger spec returned 404s, suggesting the API surface is not fully public or documented. missing for 10: explicit API-UI parity documentation, public OpenAPI spec, evidence of invoice creation/reconciliation/AI Close being API-accessible.

   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”
   • [claimed-docs] “Need to post more than one manual journal entry at a time? Instead of adding them one by one, you can upload a batch of entries all at once …”
   • [claimed-docs] “If you need to bulk add or edit your Chart of Accounts in Puzzle, you can do so by uploading a CSV file directly from your Company Settings.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://help.puzzle.io/openapi.json, https://help.puzzle.io/swagger.json, https://help.puzzle.io/api…”

   proof ↗⚑ flag

   Digits~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Puzzle
   Puzzle~partialclaimed7/10

   Puzzle documents exporting a full general ledger and financial statements in open formats (Excel, CSV, PDF) for both cash and accrual basis, which supports the core 'export and leave' requirement for financial data. missing for 10: evidence of exporting full account configuration/rules/invoice templates/all metadata, independent user corroboration of the export process, and no explicit data-portability/deletion guarantee.

   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats”
   • [claimed-docs] “Yes, you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”

   proof ↗⚑ flag

   Digits~partialclaimed4/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Puzzle—none0/10

   No evidence pack item mentions data residency, regional storage options, or any control over where customer data is hosted; Puzzle is an accounting SaaS and this is a fair question for a data platform, but nothing documents such a capability.

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Puzzle—none0/10

   No evidence pack items address data retention policies, deletion controls, or data lifecycle management for user/financial data; the evidence covers accounting features, AI Close, exports, and MCP integration but nothing on retention/deletion controls.

   ⚑ flag

   Digits—none0/10

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

   ⚑ flag

Ai insights

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

   weight 3 · round to Digits
   Puzzle✓fullclaimed7/10

   Puzzle's MCP integration explicitly connects an AI agent (Claude) to live financial data 'through natural conversation—no exports, no copy-pasting,' and Puzzle's broader API/AI messaging promotes asking plain-English questions like 'Am I ready to raise?' or 'Which months am I actually profitable?' grounded in the ledger. This directly matches the ai-native 'can we afford X' use case backed by live API data. Missing for 10: independent/hands-on verification of accuracy for financial affordability queries, and no explicit example matching the exact 'can we afford X' phrasing.

   • [claimed-docs] “Puzzle's MCP (Model Context Protocol) integration lets you connect your Puzzle account directly to Claude, giving you instant access to your…”
   • [claimed-docs] “lets you connect your Puzzle account directly to Claude, giving you instant access to your financial data through natural conversation — no …”
   • [claimed-docs] “Ask anything about your business, instantly, in plain English. "How's my cash trending?" "Am I ready to raise?" "Which months am I actually …”
   • [claimed-docs] “With Puzzle's Embedded Accounting—powered by our API, your platform gets automated AI bookkeeping, real-time financial insights, and a clean…”
   • [claimed-docs] “Our API was originally architected for deep platform-to-platform integrations.”

   proof ↗⚑ flag

   Digits✓fullprobed9/10

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

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

   proof ↗⚑ flag

Custom reports

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

   weight 2 · round drawn
   Puzzle~partialclaimed5/10

   Puzzle supports Classes with Groups (puzzle-docs-36) and general ledger/financial statement export in cash or accrual basis (puzzle-docs-26/37/45), plus multi-entity management (puzzle-docs-38/44), but there is no direct evidence of a custom report builder that lets accountants filter/group specifically by class, location, or tag dimensions together. missing for 10: explicit custom report builder UI, evidence of 'location' and 'tag' dimensions (only 'class' is documented), and confirmation that reports can be filtered/grouped by these dimensions simultaneously.

   • [claimed-docs] “a user can create an unlimited number of Groups for Classes”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats”
   • [claimed-docs] “Yes, you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “Puzzle supports managing multiple companies (entities) under one login.”

   proof ↗⚑ flag

   Digits~partialclaimed5/10

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

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

   proof ↗⚑ flag

Statements

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

   weight 3 · round to Digits
   Puzzle✓fullclaimed7/10

   Puzzle explicitly supports generating and exporting full general ledger and financial statements (cash or accrual basis) in Excel/CSV/PDF on demand, plus real-time reporting and startup metrics like ARR/burn/runway, which directly serves the founder's need for on-demand P&L/balance sheet/cash-flow reporting. Missing for 10: explicit naming of 'balance sheet' and 'cash-flow statement' as distinct statement types, and independent/hands-on verification of statement accuracy beyond vendor docs.

   • [claimed-docs] “Get real-time financial reports with one click”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats”
   • [claimed-docs] “Yes, you can export a full general ledger and financial statements on either cash or accrual basis in excel, csv, and pdf formats.”
   • [claimed-docs] “Cash **_and_** accrual accounting”
   • [claimed-docs] “Instantly see startup metrics like ARR, burn, & runway”

   proof ↗⚑ flag

   Digits✓fullclaimed8/10

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

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

   proof ↗⚑ flag