# Intercom — API Agent Score

> Score: 81/100 (Grade: A) | Domain: intercom.com | Rubric: 1.0.0 | Checked: July 24, 2026

Intercom scored 81/100 (A), classified "ai-ready".

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

## Summary

- Overall: 81/100 (A)
- Classification: ai-ready

## Category Scores

- API Design: 96/100 (A+)
- Developer Experience: 79/100 (B)
- Agent Discovery: 79/100 (B)
- Agent Understanding: 78/100 (B)
- Agent Usability: 74/100 (B)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="2.15") and header-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Schema coverage & depth — Medium parameter complexity (avg 1.8 params/op; nested/body schemas present). Investigated: spec 83%, sdk 81%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 100%.
- [pass] Example coverage — 90% example coverage across params + responses. Investigated: spec 100%, docs 100%, sdk 100%.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://www.intercom.com/signup; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Code samples in docs — Code samples in 5 language(s) across docs (top: http, curl, ruby); 3/20 pages have ≥ 2 languages on the same page. Investigated: docs 100%.
- [pass] Description completeness — 65% description completeness (target 90%+). Investigated: spec 100%, sdk 0%.
- [pass] Changelog published — changelog documented in the docs site at https://developers.intercom.com/docs/references/1.0/changelog. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (intercom/intercom-openapi, 609 snippets). Investigated: docs 100%, sdk 100%, cli 0%, mcp 0%, wellknown 0%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/50 sampled pages return markdown). Investigated: docs 75%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt directive found in HTML of any of 50 sampled pages. Investigated: docs 50%, sdk 0%.
- [warn] Crawlable / AEO — Sitemap present (6039 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 7 distinct 4xx/5xx response codes documented. Investigated: docs 100%, sdk 100%, spec 50%.
- [pass] Operation purpose clarity — 98% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — 27 of 50 pages have substantive content differences between markdown and HTML (avg 24% missing). Investigated: docs 72%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 20 sampled pages — likely a CSR-only docs site. Investigated: docs 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] Pagination documented & consistent — Pagination params detected on 30 list endpoint(s). Investigated: spec 100%, docs 100%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Intercom's API program has a strong foundation in API design, with a well-typed, machine-readable contract partners can build against. The most urgent gaps are in agent understanding and agent usability: there are no agent instruction files, no structured metadata for AI crawlers, and no runnable collections with test scripts — meaning AI agents and partners alike must guess at integration patterns rather than execute against verified, current examples. Prioritize making your APIs immediately executable and machine-interpretable to unlock self-serve partner onboarding and reliable agent-driven integrations.