Useparagonuseparagon.com

ScoredJul 24, 2026, 11:16 AM

Useparagon's API program shows strength in agent understanding and discovery fundamentals, but two areas are holding back partner outcomes: developer onboarding is slow and self-serve (partners cannot get hands-on without friction), and agents lack the runnable context and structured instructions they need to integrate reliably. Prioritize closing the onboarding gap and establishing executable, agent-ready artifacts first — these directly determine whether partners and their AI agents can reach a first successful integration without a sales conversation or support escalation.

API DesignA clean, typed, well-governed API contract agents can reason about1 pass1 warn1 fail72B
SignalPointsFindingsRationale
warnSchema coverage & depthvia sdk22.8/2511 of 361 public signatures use loose types (anyTypeRatio=0.030). Investigated: sdk 91%.Typed, complete request/response schemas are what make agent function-calling possible.
passExample coveragevia sdk10/10README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.Examples carry shape semantics schemas under-specify — for humans and agents alike.
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.
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.
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 warn2 fail54D
SignalPointsFindingsRationale
passQuickstart presentvia docs25/25Quickstart at https://docs.useparagon.com/getting-started/installing-the-connect-sdk with a runnable first-call sample. Investigated: docs 100%.A quickstart is the fastest path from landing page to first successful call.
warnDescription completenessvia sdk8/1569/148 operations lack a description. Investigated: sdk 53%.Complete descriptions are the context humans and agents need to use endpoints.
failSelf-service developer portalvia docs0/29No 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.
failCode samples in docsvia docs0/18No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.Multi-language samples shorten time-to-first-call.
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 docs2 pass2 warn0 fail76B
SignalPointsFindingsRationale
passDocs reachable, not hard auth-gatedvia docs30/30All 1 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.
warnllms.txt present, valid & comprehensivevia docs15/30llms.txt covers 0/1 sitemap doc pages (0%); 1 missing. Investigated: docs 50%, sdk 0%.A valid, comprehensive llms.txt is the machine-readable entry point for agents.
warnRegistry & SDK presencevia sdk14/28No official SDKs discovered via npm, PyPI, or GitHub. Investigated: sdk 50%, docs 0%, cli 0%.Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look.
passCrawlable / AEOvia wellknown12/12Docs 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 fail83A
SignalPointsFindingsRationale
passMachine-readable errors (RFC 9457)via sdk28/28Single base error "BaseSDKError" with 49 subclasses. Investigated: sdk 100%.RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens.
passAgent-navigable, token-efficient docsvia docs22/22All 1 pages contain server-rendered content. Investigated: docs 100%.Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly.
passDocs structured datavia docs8/8JSON-LD Article markup on 20/20 assessed pages (100%) 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.
warnDescription consistency across surfaces1.7/7Mean pairwise description similarity across 2 surfaces (docs, sdk) is 8% (threshold 35% for full credit).Every surface tells the same story about what the product is.
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.
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.
Agent UsabilityAgents have the context to use your APIs reliably, not just find them2 pass1 warn1 fail71B
SignalPointsFindingsRationale
passIdempotency documentedvia sdk27/27Built-in retry machinery is present (grep-derived). Investigated: sdk 100%.Documented idempotency lets agents retry safely.
passSandbox separationvia sdk20/20Sandbox environments are exposed (sandbox). Investigated: sdk 100%.An isolated environment lets agents exercise destructive operations safely.
warnPagination documented & consistentvia sdk3.7/22Only 2/12 list method(s) return an auto-paginating iterable; 10 return a raw page. Investigated: sdk 17%.Consistent, documented pagination lets agents traverse collections.
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.
naRate-limit signaling—/22No surface produced evidence for this capability in this run.Machine-readable rate-limit headers let agents throttle adaptively.
Want to improve your results?