# Duffel — API Agent Score

> Score: 54/100 (Grade: D) | Domain: duffel.com | Rubric: 1.0.0 | Checked: July 24, 2026

Duffel scored 54/100 (D), classified "not-ai-ready".

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

## Summary

- Overall: 54/100 (D)
- Classification: not-ai-ready

## Category Scores

- API Design: 60/100 (C)
- Developer Experience: 44/100 (F)
- Agent Discovery: 65/100 (C)
- Agent Understanding: 57/100 (D)
- Agent Usability: 45/100 (F)

## Check Results

### API Design

- [warn] Schema coverage & depth — 12/51 (24%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 56%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [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] Changelog published — Newest official SDK activity 2 day(s) ago. Investigated: sdk 100%.
- [warn] Description completeness — 36/46 operations lack a description. Investigated: sdk 22%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). 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 1 sampled docs pages. Investigated: docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/duffel, 745 snippets). Investigated: docs 100%, sdk 67%, cli 0%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/1 pages return markdown). Investigated: docs 75%.
- [warn] Crawlable / AEO — No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 50%.
- [fail] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://duffel.com/docs/llms.txt, https://duffel.com/llms.txt). Investigated: docs 0%, sdk 0%.

### Agent Understanding

- [warn] Agent-navigable, token-efficient docs — No pages support .md URLs (0/1 tested). Investigated: docs 86%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (docs, sdk) is 8% (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 1 assessed pages (1 JS-rendered). Investigated: docs 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.

### Agent Usability

- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [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

Duffel's API program shows meaningful strengths in schema quality and crawlability, but partners and their agents face two critical blockers today: there is no self-service onboarding path — no portal, no quickstart, no ready-to-run examples — meaning partners cannot get hands-on without a support conversation; and the program is invisible to AI agents, lacking the machine-readable discovery files and structured context agents need to find and correctly invoke the API. Closing the onboarding gap and making the API agent-discoverable should be the immediate priorities, followed by rounding out idempotency documentation and runnable test coverage to make production integrations trustworthy.