# SAP — API Agent Score

> Score: 76/100 (Grade: B) | Domain: sap.com | Rubric: 1.0.0 | Checked: July 24, 2026

SAP scored 76/100 (B), classified "partially-ready".

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

## Summary

- Overall: 76/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 97/100 (A+)
- Developer Experience: 65/100 (C)
- Agent Discovery: 77/100 (B)
- Agent Understanding: 71/100 (B)
- Agent Usability: 72/100 (B)

## Check Results

### API Design

- [warn] Schema coverage & depth — 22 of 716 public signatures use loose types (anyTypeRatio=0.031). Investigated: sdk 92%.
- [pass] Security & governance hygiene — security.txt valid at https://sap.com/.well-known/security.txt (Contact + unexpired Expires). Investigated: wellknown 100%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 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://www.sap.com/products/try-sap.html; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [warn] Description completeness — 281/304 operations carry a description. Investigated: sdk 92%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%.
- [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 1 sampled docs pages. Investigated: docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/help_sap_sap_erp, 2174 snippets). Investigated: docs 100%, sdk 92%, 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%.
- [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://developers.sap.com/llms.txt, https://developers.sap.com/docs/llms.txt). Investigated: docs 33%, sdk 0%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Single base error "SapError" with 16 subclasses. Investigated: sdk 100%.
- [warn] Agent-navigable, token-efficient docs — No sampled pages support .md URLs (0/50 tested). Investigated: docs 71%.
- [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 1 assessed pages (1 JS-rendered). Investigated: docs 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%.
- [warn] Pagination documented & consistent — Only 5/24 list method(s) return an auto-paginating iterable; 19 return a raw page. Investigated: sdk 21%.
- [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.

## Executive Summary

SAP's API program shows strong contract quality — the schema and type definitions give partners and agents a reliable foundation to build against. However, two areas need urgent attention: agents and AI coding tools lack the structured context files, machine-readable documentation, and runnable examples they need to integrate without guesswork, and partners face a slow on-ramp with no quickstart or inline code samples to reach a first successful call quickly. Prioritize closing the agent-readability and onboarding gaps first, as they directly determine whether partners and their AI agents can self-serve or stall at the starting line.