# AssemblyAI — API Agent Score

> Score: 89/100 (Grade: A) | Domain: assemblyai.com | Rubric: 1.0.0 | Checked: July 24, 2026

AssemblyAI scored 89/100 (A), classified "ai-ready".

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

## Summary

- Overall: 89/100 (A)
- Classification: ai-ready

## Category Scores

- API Design: 97/100 (A+)
- Developer Experience: 100/100 (A+)
- Agent Discovery: 93/100 (A+)
- Agent Understanding: 87/100 (A)
- Agent Usability: 73/100 (B)

## Check Results

### API Design

- [pass] Schema coverage & depth — 44/44 (100%) public params are fully typed (no any/**kwargs). Analyzer confirms all methods have a derivable input schema. Investigated: sdk 100%, spec 83%.
- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Machine-readable, versioned contract — info.version="1.3.4" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 88%, docs 75%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — 25% example coverage. Investigated: spec 100%, docs 100%, sdk 100%.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://www.assemblyai.com/dashboard/signup; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Quickstart present — Quickstart at https://www.assemblyai.com/docs/ with a runnable first-call sample. Investigated: docs 100%.
- [pass] Code samples in docs — Code samples in 4 language(s) across docs (top: shell, python, javascript); 2/17 pages have ≥ 2 languages on the same page. Investigated: docs 100%.
- [pass] Description completeness — 75% description completeness (target 90%+). Investigated: spec 100%, sdk 78%.
- [pass] Changelog published — changelog documented in the docs site at https://www.assemblyai.com/changelog. Investigated: spec 100%, docs 100%, sdk 100%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/assemblyai, 9870 snippets). Investigated: docs 100%, sdk 100%, cli 100%.
- [warn] llms.txt present, valid & comprehensive — llms.txt directive found in HTML of 47 of 49 sampled pages (2 missing); 1 failed to fetch. Investigated: docs 88%, sdk 0%.
- [warn] Docs reachable, not hard auth-gated — 1 of 50 sampled pages use cross-host redirects. Investigated: docs 88%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — No explicit 4xx/5xx codes, but 2 operation(s) document a "default" error response. Investigated: docs 100%, sdk 100%, spec 50%.
- [pass] Operation purpose clarity — 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — 10 of 47 pages have minor content differences between markdown and HTML. Investigated: docs 83%.
- [pass] Docs structured data — JSON-LD Article markup on 5/6 assessed pages (83%) with dateModified present (1 JS-rendered). Investigated: docs 100%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [warn] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 25%, docs 25%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

AssemblyAI's API program shines in contract quality, documentation discovery, and overall API design — partners and agents can find and read the surface with confidence. The two areas that need immediate attention are agent-facing context and runnable proof: there is no structured file guiding AI agents on how to use the API, and there are no executable collections with test scripts to give partners and their coding agents verified, working examples. Closing these two gaps will meaningfully accelerate partner integration and make the API reliably usable by autonomous agents.