# AT&T — API Agent Score

> Score: 65/100 (Grade: C) | Domain: att.com | Rubric: 1.0.0 | Checked: July 24, 2026

AT&T scored 65/100 (C), classified "partially-ready".

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

## Summary

- Overall: 65/100 (C)
- Classification: partially-ready

## Category Scores

- API Design: 91/100 (A+)
- Developer Experience: 58/100 (D)
- Agent Discovery: 66/100 (C)
- Agent Understanding: 74/100 (B)
- Agent Usability: 45/100 (F)

## Check Results

### API Design

- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%, wellknown 0%.
- [warn] Schema coverage & depth — 10/11 parameters are deeply nested or free-form maps. Investigated: sdk 85%, spec 83%.
- [warn] Machine-readable, versioned contract — info.version="1.0.0" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — 43% example coverage. Investigated: spec 100%, sdk 100%, docs 0%.

### Developer Experience

- [pass] Self-service developer portal — Self-service signup at https://www.wireless.att.com/businesscare/registration/self-registration.jsp?source=EBP3EL00000ONB00D&wtExtndSource=WEREG&LNS=DM_MB_MG_VTSRBALVBIV_1119; free tier / sandbox documented. Investigated: docs 100%.
- [pass] Description completeness — 50% description completeness. Investigated: spec 100%, sdk 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 19 sampled docs pages. Investigated: docs 0%.
- [fail] Changelog published — No changelog URL or mention found in spec metadata. Investigated: spec 0%, docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (mitre-attack/attack-stix-data, 98 snippets). Investigated: docs 100%, sdk 100%, cli 0%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.
- [fail] llms.txt present, valid & comprehensive — No /llms-full.txt found at the candidate origins. Investigated: docs 0%, sdk 0%.
- [skip] Docs reachable, not hard auth-gated — No surface produced evidence for this capability in this run.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Only 1 distinct 4xx/5xx codes documented (plus 0 "default" catch-all responses). Investigated: docs 100%, spec 50%.
- [pass] Operation purpose clarity — 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (spec, sdk) is 3% (threshold 35% for full credit).
- [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 3 assessed pages (3 JS-rendered). Investigated: docs 0%.
- [skip] Agent-navigable, token-efficient docs — No surface produced evidence for this capability in this run.

### Agent Usability

- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [fail] Pagination documented & consistent — 1 list endpoint(s) exist but no pagination params found. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

AT&T's API Design is a genuine strength — the machine-readable contract and schema quality give partners and agents a solid foundation to build against. However, two areas are actively blocking partner program growth: agents and integration tools cannot reliably execute real workflows because idempotency, rate-limit signaling, pagination, and runnable collections are all missing; and partners struggle to self-serve onboard because there is no changelog, no quickstart, no code samples, and no discoverable front door for agents (llms.txt, AGENTS.md, or structured docs metadata). Prioritize making the API operationally trustworthy and executable first, then close the discovery and onboarding gaps so partners and their AI agents can find, understand, and integrate without a sales conversation.