# Finch — API Agent Score

> Score: 77/100 (Grade: B) | Domain: tryfinch.com | Rubric: 1.0.0 | Checked: July 24, 2026

Finch scored 77/100 (B), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/tryfinch)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 77/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 100/100 (A+)
- Developer Experience: 49/100 (F)
- Agent Discovery: 98/100 (A+)
- Agent Understanding: 71/100 (B)
- Agent Usability: 71/100 (B)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="2020-09-17") and header-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Schema coverage & depth — 4/4 enums are named types (not bare strings). Investigated: sdk 100%, spec 83%.
- [pass] Auth declared & discoverable — authentication documented in the docs site at https://developer.tryfinch.com/api-reference/management/create-access-token. Investigated: spec 100%, docs 100%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — 54% example coverage (target 80%+). Investigated: spec 100%, sdk 100%, docs 0%.

### Developer Experience

- [pass] Description completeness — 93% of operations + parameters have substantive descriptions. Investigated: spec 100%.
- [pass] Changelog published — changelog documented in the docs site at https://developer.tryfinch.com/changelog. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.
- [fail] Code samples in docs — No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.

### Agent Discovery

- [pass] Docs reachable, not hard auth-gated — All 50 sampled pages are publicly accessible. Investigated: docs 100%.
- [warn] llms.txt present, valid & comprehensive — llms.txt contains parseable links but doesn't fully follow the proposed structure: https://developer.tryfinch.com/llms.txt: No blockquote summary found. Investigated: docs 94%, sdk 0%.
- [pass] Registry & SDK presence — Indexed on Context7 (llmstxt/developer_tryfinch_llms_txt, 2159 snippets). Investigated: docs 100%, sdk 58%, cli 0%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 5 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%.
- [warn] Agent-navigable, token-efficient docs — 3 of 49 pages have substantive content differences between markdown and HTML (avg 4% missing). Investigated: docs 67%.
- [warn] Operation purpose clarity — 90% of operations are agent-inferable (target 90%+). Investigated: spec 50%.
- [pass] Docs structured data — JSON-LD Article markup on 20/20 assessed pages (100%) with dateModified present. Investigated: docs 100%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (spec, docs) is 4% (threshold 35% for full credit).
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.

### Agent Usability

- [pass] Rate-limit signaling — rate-limit behavior documented in the docs site at https://developer.tryfinch.com/api-reference/development-guides/Rate-Limits. Investigated: spec 100%, docs 100%.
- [pass] Pagination documented & consistent — Pagination params detected on 8 list endpoint(s). Investigated: spec 100%, docs 100%.
- [pass] Sandbox separation — sandbox documented in the docs site at https://developer.tryfinch.com/api-reference/sandbox/create-sandbox-account. Investigated: spec 100%, docs 100%, sdk 50%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Tryfinch's agent discoverability is a clear strength — documentation is easy to find and well-structured. However, the partner program has two critical gaps that will slow adoption and integration: there is no self-service onboarding path, leaving partners without a portal, quickstart, or code samples to get hands-on quickly; and there is no machine-readable agent context or runnable collection, meaning AI coding agents cannot reliably discover, understand, or execute against Tryfinch's APIs. Prioritize building a self-service developer experience first, then close the agent-readiness gaps to ensure both human partners and their AI agents can integrate with confidence.