Wandbwandb.ai
Wandb's API program shows strong foundations in discovery, contract readability, and documentation parseability — partners and agents can find and read your APIs with relative ease. The two areas that need immediate attention are agent-facing context and runnable integration assets: there is no structured file telling AI agents how to work with your APIs, and partners lack executable, test-backed collections to validate real workflows.
API DesignA clean, typed, well-governed API contract agents can reason about3 pass2 warn0 fail88A
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Auth declared & discoverablevia spec | 25/25 | authentication documented in the docs site at https://docs.wandb.ai/inference/prerequisites. Investigated: spec 100%, docs 100%. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
| warn | Machine-readable, versioned contractvia spec | 18.8/25 | info.version="0.1.0" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| warn | Schema coverage & depthvia sdk | 17.1/25 | 12 of 95 public signatures use loose types (anyTypeRatio=0.126). Investigated: sdk 68%, spec 67%. | Typed, complete request/response schemas are what make agent function-calling possible. |
| pass | Security & governance hygienevia spec | 15/15 | No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 50%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| pass | Example coveragevia sdk | 10/10 | README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 0%, docs 0%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples3 pass1 warn1 fail79B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Self-service developer portalvia docs | 29/29 | Signup page at https://wandb.ai/signup (CSR-rendered — body classifier inconclusive); free tier / sandbox documented in pricing/docs. Investigated: docs 100%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| pass | Quickstart presentvia docs | 25/25 | Quickstart at https://docs.wandb.ai/models/quickstart with a runnable first-call sample. Investigated: docs 100%. | A quickstart is the fastest path from landing page to first successful call. |
| pass | Changelog publishedvia spec | 13/13 | changelog documented in the docs site at https://docs.wandb.ai/release-notes. Investigated: spec 100%, docs 100%, sdk 100%. | A published changelog lets partners track changes without surprise. |
| warn | Description completenessvia sdk | 7.5/15 | 915/1821 operations lack a description. Investigated: sdk 50%, spec 0%. | Complete descriptions are the context humans and agents need to use endpoints. |
| fail | Code samples in docsvia docs | 0/18 | No detectable code samples across 20 sampled docs pages. Investigated: docs 0%. | Multi-language samples shorten time-to-first-call. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs3 pass1 warn0 fail92A+
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Docs reachable, not hard auth-gatedvia docs | 30/30 | All 50 sampled pages are publicly accessible. Investigated: docs 100%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| pass | Registry & SDK presencevia docs | 28/28 | Indexed on Context7 (wandb/wandb, 2146 snippets). Investigated: docs 100%, cli 100%, sdk 92%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | llms.txt present, valid & comprehensivevia docs | 20.6/30 | llms.txt covers 865/1163 sitemap doc pages (74%); 298 missing; 26 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap). Investigated: docs 69%, sdk 0%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| pass | Crawlable / AEOvia wellknown | 12/12 | Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs3 pass1 warn1 fail85A
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Machine-readable errors (RFC 9457)via docs | 28/28 | Only 1 distinct 4xx/5xx codes documented (plus 0 "default" catch-all responses). Investigated: docs 100%, spec 50%, sdk 0%. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| pass | Operation purpose clarityvia spec | 25/25 | 92% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| warn | Agent-navigable, token-efficient docsvia docs | 15.4/22 | 14 of 50 pages have substantive content differences between markdown and HTML (avg 14% missing). Investigated: docs 70%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| pass | Docs structured datavia docs | 8/8 | JSON-LD Article markup on 19/20 assessed pages (95%) with dateModified present. Investigated: docs 100%. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| fail | Agent instructions file (AGENTS.md)via wellknown | 0/10 | No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%. | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
| na | Description consistency across surfaces | —/7 | Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare. | Every surface tells the same story about what the product is. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them3 pass0 warn2 fail74B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Idempotency documentedvia sdk | 27/27 | Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%. | Documented idempotency lets agents retry safely. |
| pass | Rate-limit signalingvia spec | 22/22 | rate-limit behavior documented in the docs site at https://docs.wandb.ai/platform/hosting/hosting-options/dedicated-cloud/rate-limits. Investigated: spec 100%, docs 100%. | Machine-readable rate-limit headers let agents throttle adaptively. |
| pass | Sandbox separationvia spec | 20/20 | sandbox documented in the docs site at https://docs.wandb.ai/sandboxes/invoke-agent-sandbox-tutorial. Investigated: spec 100%, docs 100%, sdk 100%. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Pagination documented & consistentvia spec | 0/22 | 2 list endpoint(s) exist but no pagination params found. Investigated: spec 0%, docs 0%, sdk 0%. | Consistent, documented pagination lets agents traverse collections. |
| fail | Runnable collection with test scriptsvia platform | 0/9 | No public Postman workspace discovered for the org. Investigated: platform 0%. | A public, maintained collection with assertions is runnable truth agents validate against. |
Resources Discovered
The public resources we found for Wandb — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (2,146) |
|---|---|
| APIs analyzed | 1 — FastAPI |