# Sendbird — API Agent Score

> Score: 74/100 (Grade: B) | Domain: sendbird.com | Rubric: 1.0.0 | Checked: July 24, 2026

Sendbird scored 74/100 (B), classified "partially-ready".

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

## Summary

- Overall: 74/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 72/100 (B)
- Developer Experience: 78/100 (B)
- Agent Discovery: 96/100 (A+)
- Agent Understanding: 58/100 (D)
- Agent Usability: 72/100 (B)

## Check Results

### API Design

- [warn] Schema coverage & depth — 18 of 700 public signatures use loose types (anyTypeRatio=0.026). Investigated: sdk 93%.
- [pass] Example coverage — Code samples present on 1/19 pages across 1 language(s); broader multi-language coverage missing. Investigated: docs 100%, sdk 100%.
- [fail] Security & governance hygiene — No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://sendbird.com/free-trial; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Code samples in docs — Code samples present on 1/19 pages across 1 language(s); broader multi-language coverage missing. Investigated: docs 100%.
- [warn] Description completeness — 317/340 operations carry a description. Investigated: sdk 93%.
- [pass] Changelog published — Newest official SDK activity 10 day(s) ago. Investigated: sdk 100%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.

### Agent Discovery

- [pass] llms.txt present, valid & comprehensive — llms-full.txt reachable at https://sendbird.com/docs/llms-full.txt. Investigated: docs 100%, sdk 0%.
- [pass] Registry & SDK presence — Indexed on Context7 (websites/sendbird, 56460 snippets). Investigated: docs 100%, sdk 100%, cli 0%, mcp 0%, wellknown 0%.
- [warn] Crawlable / AEO — robots.txt blocks 3 of 7 monitored AI crawlers on docs paths (gptbot, google-extended, ccbot). Investigated: wellknown 75%.
- [skip] Docs reachable, not hard auth-gated — No surface produced evidence for this capability in this run.

### Agent Understanding

- [pass] Docs structured data — JSON-LD Article markup on 16/19 assessed pages (84%) with dateModified present. Investigated: docs 100%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Machine-readable errors (RFC 9457) — No surface produced evidence for this capability in this run.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.
- [skip] Agent-navigable, token-efficient docs — No surface produced evidence for this capability in this run.
- [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%.
- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Sendbird's API program shows strong discoverability fundamentals, but two areas put partner and agent adoption at risk: agent-facing context is effectively absent, and runnable proof-of-work for integrations is missing. Until partners and their AI agents have machine-readable instructions and executable collections to build against, onboarding will stall on support tickets rather than self-serve success. Prioritize closing the agent-context and runnable-truth gaps first, then harden auth governance and quickstart coverage to complete the partner-ready picture.