Anyscaleanyscale.com
Anyscale's API program shows strong discoverability fundamentals, but partners and their AI agents hit a wall once they arrive: there are no machine-readable agent instructions, no structured data for AI parsing, and no runnable collection to validate real workflows. These gaps mean agents building on Anyscale's APIs must guess at context, cannot self-orient, and have no executable ground truth to work from — all of which slow partner integration and erode trust.
API DesignA clean, typed, well-governed API contract agents can reason about1 pass1 warn0 fail75B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Example coveragevia docs | 10/10 | Code samples present on 5/20 pages across 2 language(s); broader multi-language coverage missing. Investigated: docs 100%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
| warn | Security & governance hygienevia wellknown | 7.5/15 | security.txt present but served only at the legacy /security.txt path; missing Contact; missing or expired Expires. Investigated: wellknown 50%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| na | Machine-readable, versioned contract | —/25 | No surface produced evidence for this capability in this run. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| na | Schema coverage & depth | —/25 | No surface produced evidence for this capability in this run. | Typed, complete request/response schemas are what make agent function-calling possible. |
| na | Auth declared & discoverable | —/25 | No surface produced evidence for this capability in this run. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples2 pass0 warn1 fail68C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Quickstart presentvia docs | 25/25 | Quickstart at https://docs.anyscale.com/get-started with a runnable first-call sample. Investigated: docs 100%. | A quickstart is the fastest path from landing page to first successful call. |
| pass | Code samples in docsvia docs | 18/18 | Code samples present on 5/20 pages across 2 language(s); broader multi-language coverage missing. Investigated: docs 100%. | Multi-language samples shorten time-to-first-call. |
| fail | Self-service developer portalvia docs | 0/29 | Signup page is sales-gated (contact-sales/request-access language detected). Investigated: docs 0%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| na | Description completeness | —/15 | No surface produced evidence for this capability in this run. | Complete descriptions are the context humans and agents need to use endpoints. |
| na | Changelog published | —/13 | No surface produced evidence for this capability in this run. | A published changelog lets partners track changes without surprise. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs2 pass2 warn0 fail88A
| 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 (websites/anyscale, 8498 snippets). Investigated: docs 100%, sdk 50%, cli 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | llms.txt present, valid & comprehensivevia docs | 22.5/30 | llms.txt covers 273/498 sitemap doc pages (55%); 225 missing. Investigated: docs 75%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| warn | Crawlable / AEOvia wellknown | 6/12 | robots.txt blocks 4 of 7 monitored AI crawlers on docs paths (gptbot, claudebot, google-extended, ccbot). Investigated: wellknown 50%. | 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 docs0 pass1 warn2 fail59D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Agent-navigable, token-efficient docsvia docs | 18.3/22 | 1 of 50 sampled pages have content starting past 50% (worst 67%). Investigated: docs 83%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| 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. |
| fail | Docs structured datavia docs | 0/8 | Neither JSON-LD nor OpenGraph/meta tags detected across 3 assessed pages (3 JS-rendered). Investigated: docs 0%. | 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. |
| na | Machine-readable errors (RFC 9457) | —/28 | No surface produced evidence for this capability in this run. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| na | Operation purpose clarity | —/25 | No surface produced evidence for this capability in this run. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| 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 them0 pass0 warn1 fail40F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| 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. |
| na | Idempotency documented | —/27 | No surface produced evidence for this capability in this run. | Documented idempotency lets agents retry safely. |
| na | Rate-limit signaling | —/22 | No surface produced evidence for this capability in this run. | Machine-readable rate-limit headers let agents throttle adaptively. |
| na | Pagination documented & consistent | —/22 | No surface produced evidence for this capability in this run. | Consistent, documented pagination lets agents traverse collections. |
| na | Sandbox separation | —/20 | No surface produced evidence for this capability in this run. | An isolated environment lets agents exercise destructive operations safely. |
Resources Discovered
The public resources we found for Anyscale — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (8,498) |
|---|