Replicatereplicate.com
Replicate's API design and discoverability are strong foundations for a partner program, but two areas need urgent attention: partners and their AI agents currently lack the structured context, machine-readable instructions, and runnable examples needed to integrate confidently — and the onboarding experience creates unnecessary friction with no self-service portal and sparse code samples. Prioritizing agent-readable documentation, a self-service portal with embedded code samples, and runnable collections with test coverage will directly compress the time partners spend evaluating and integrating, while making Replicate's APIs reliably actionable for the AI-powered workflows partners are increasingly building.
API DesignA clean, typed, well-governed API contract agents can reason about4 pass1 warn0 fail95A+
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Machine-readable, versioned contractvia spec | 25/25 | Versioning declared (info.version="1.0.0-a1") and url-versioning detected. Investigated: spec 100%, docs 100%. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| pass | Auth declared & discoverablevia spec | 25/25 | Authentication required (global or on every operation). Investigated: spec 100%, docs 100%. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
| warn | Schema coverage & depthvia sdk | 19.5/25 | 30 of 158 public signatures use loose types (anyTypeRatio=0.190). Investigated: sdk 78%, 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 0%. | 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 examples2 pass1 warn2 fail55D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Description completenessvia spec | 15/15 | 99% of operations + parameters have substantive descriptions. Investigated: spec 100%, sdk 80%. | Complete descriptions are the context humans and agents need to use endpoints. |
| pass | Changelog publishedvia spec | 13/13 | changelog documented in the docs site at https://replicate.com/changelog. Investigated: spec 100%, docs 100%, sdk 50%. | A published changelog lets partners track changes without surprise. |
| warn | Quickstart presentvia docs | 12.5/25 | Quickstart page reachable (1 variants scanned starting at https://replicate.com/docs) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%. | A quickstart is the fastest path from landing page to first successful call. |
| fail | Self-service developer portalvia docs | 0/29 | 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%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| fail | Code samples in docsvia docs | 0/18 | No detectable code samples across 1 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 docs2 pass2 warn0 fail86A
| 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/replicate, 1234 snippets). Investigated: docs 100%, cli 100%, sdk 67%, mcp 0%, wellknown 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | llms.txt present, valid & comprehensivevia docs | 17.1/30 | Only 44/50 same-origin sampled links resolve (88%); 6 broken. Investigated: docs 57%, sdk 0%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| warn | Crawlable / AEOvia wellknown | 9/12 | Sitemap lastmod coverage 50% or newest entry older than 90 days. Investigated: wellknown 75%. | 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 docs2 pass2 warn2 fail74B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Machine-readable errors (RFC 9457)via docs | 28/28 | 4 distinct 4xx/5xx response codes documented. Investigated: docs 100%, sdk 100%, spec 50%. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| pass | Operation purpose clarityvia spec | 25/25 | 100% 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 | 13.2/22 | 8 of 45 pages have substantive content differences between markdown and HTML (avg 14% missing). Investigated: docs 60%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| warn | Description consistency across surfaces | 2.2/7 | Mean pairwise description similarity across 3 surfaces (spec, docs, sdk) is 11% (threshold 35% for full credit). | Every surface tells the same story about what the product is. |
| 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 1 assessed pages (1 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. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them2 pass1 warn2 fail73B
| 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. |
| warn | Pagination documented & consistentvia sdk | 20.5/22 | 14/15 list method(s) return an auto-paginating iterable. Investigated: sdk 93%, spec 0%, docs 0%. | Consistent, documented pagination lets agents traverse collections. |
| pass | Sandbox separationvia sdk | 20/20 | Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Rate-limit signalingvia spec | 0/22 | No rate-limit response headers documented. Investigated: spec 0%, docs 0%. | Machine-readable rate-limit headers let agents throttle adaptively. |
| 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 Replicate — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (1,234) |
|---|---|
| APIs analyzed | 1 — Replicate HTTP API |