Kaiserpermanentekaiserpermanente.org

ScoredJul 24, 2026, 07:59 AM

Kaiser Permanente's API program shows some progress in documentation reachability and crawlability, but two areas demand immediate attention: API design fundamentals and agent readiness. Missing security hygiene, absent request/response examples, and no runnable collections mean partners and their AI agents cannot confidently build against your APIs — creating friction that stalls integrations and erodes trust.

API DesignA clean, typed, well-governed API contract agents can reason about0 pass0 warn2 fail40F
SignalPointsFindingsRationale
failSecurity & governance hygienevia wellknown0/15No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%.No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel.
failExample coveragevia docs0/10No detectable code samples across 1 sampled docs pages. Investigated: docs 0%.Examples carry shape semantics schemas under-specify — for humans and agents alike.
naMachine-readable, versioned contract—/25No surface produced evidence for this capability in this run.A current OpenAPI version with a declared versioning scheme lets agents reason about the contract.
naSchema coverage & depth—/25No surface produced evidence for this capability in this run.Typed, complete request/response schemas are what make agent function-calling possible.
naAuth declared & discoverable—/25No 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 examples1 pass1 warn1 fail66C
SignalPointsFindingsRationale
passSelf-service developer portalvia docs29/29Self-service signup at https://healthy.kaiserpermanente.org/register?kp_shortcut_referrer=kp.org/signup; no free tier or sandbox language detected. Investigated: docs 100%.Self-serve key/account creation is the fast first call for partners, with no sales gate.
warnQuickstart presentvia docs12.5/25Quickstart page reachable (10 variants scanned starting at https://developer.kp.org/quickstart) 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.
failCode samples in docsvia docs0/18No detectable code samples across 1 sampled docs pages. Investigated: docs 0%.Multi-language samples shorten time-to-first-call.
naDescription completeness—/15No surface produced evidence for this capability in this run.Complete descriptions are the context humans and agents need to use endpoints.
naChangelog published—/13No 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 docs0 pass3 warn1 fail52D
SignalPointsFindingsRationale
warnDocs reachable, not hard auth-gatedvia docs15/301 of 1 pages return 200 for non-existent URLs (soft 404). Investigated: docs 50%.Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics.
warnllms.txt present, valid & comprehensivevia docs10/30No llms.txt found at any candidate location (https://developer.kp.org/llms.txt, https://developer.kp.org/docs/llms.txt). Investigated: docs 33%.A valid, comprehensive llms.txt is the machine-readable entry point for agents.
warnCrawlable / AEOvia wellknown9/12Sitemap present (0 entries) but carries no lastmod values. Investigated: wellknown 75%.Bots allowed plus a fresh sitemap make docs findable by agent crawlers.
failRegistry & SDK presencevia docs0/28Not indexed on Context7 — agents can't pull this API's docs on demand via Context7. Investigated: docs 0%, sdk 0%, cli 0%.Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look.
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs0 pass1 warn2 fail55D
SignalPointsFindingsRationale
warnAgent-navigable, token-efficient docsvia docs15.7/22No pages support .md URLs (0/1 tested). Investigated: docs 71%.Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly.
failAgent instructions file (AGENTS.md)via wellknown0/10No 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.
failDocs structured datavia docs0/8Neither JSON-LD nor OpenGraph/meta tags detected across 1 sampled pages — likely a CSR-only docs site. 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.
naMachine-readable errors (RFC 9457)—/28No 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.
naOperation purpose clarity—/25No 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.
naDescription consistency across surfaces—/7Only 0 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
SignalPointsFindingsRationale
failRunnable collection with test scriptsvia platform0/9No public Postman workspace discovered for the org. Investigated: platform 0%.A public, maintained collection with assertions is runnable truth agents validate against.
naIdempotency documented—/27No surface produced evidence for this capability in this run.Documented idempotency lets agents retry safely.
naRate-limit signaling—/22No surface produced evidence for this capability in this run.Machine-readable rate-limit headers let agents throttle adaptively.
naPagination documented & consistent—/22No surface produced evidence for this capability in this run.Consistent, documented pagination lets agents traverse collections.
naSandbox separation—/20No surface produced evidence for this capability in this run.An isolated environment lets agents exercise destructive operations safely.
Want to improve your results?