# Orange — API Agent Score

> Score: 72/100 (Grade: B) | Domain: orange.com | Rubric: 1.0.0 | Checked: July 30, 2026

Orange scored 72/100 (B), classified "partially-ready".

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

## Summary

- Overall: 72/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 79/100 (B)
- Developer Experience: 49/100 (F)
- Agent Discovery: 69/100 (C)
- Agent Understanding: 75/100 (B)
- Agent Usability: 86/100 (A)

## Check Results

### API Design

- [warn] Schema coverage & depth — 45 of 425 public signatures use loose types (anyTypeRatio=0.106). Investigated: sdk 81%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [warn] Security & governance hygiene — security.txt present but missing Contact; missing or expired Expires. Investigated: wellknown 50%.
- [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

- [warn] Description completeness — 395/396 operations carry a description. Investigated: sdk 100%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%.
- [fail] Self-service developer portal — Signup page is sales-gated (contact-sales/request-access language detected). 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] Registry & SDK presence — Indexed on Context7 (cloudflare/orange, 6 snippets). Investigated: docs 100%, sdk 67%, cli 50%.
- [warn] Docs reachable, not hard auth-gated — All 1 pages require authentication. Investigated: docs 40%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://developer.orange.com/llms.txt, https://developer.orange.com/docs/llms.txt). Investigated: docs 33%, sdk 0%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Single base error "SDKException" with 13 subclasses. Investigated: sdk 100%.
- [warn] Agent-navigable, token-efficient docs — No pages support .md URLs (0/1 tested). Investigated: docs 71%.
- [warn] Docs structured data — OpenGraph/meta tags only across 20 assessed pages — no JSON-LD for answer engines to cite. Investigated: docs 50%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Operation purpose clarity — 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%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%.
- [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

Orange's API program shows strength in agent discoverability and API design fundamentals, but the partner onboarding experience is the most critical gap — all three onboarding signals are failing, meaning partners currently have no self-service path to evaluate or integrate with the APIs. Closely behind, AI agents lack the structured instruction context and runnable workflow examples they need to integrate reliably without guessing. Prioritize creating a self-service portal with quickstarts and code samples first, then layer in agent-specific context and executable collections to ensure both human partners and their AI agents can go from discovery to working integration without friction.