03 / Scorecard / Observability
Patronus AI
F
Headless Index
25/100
denominator 60
JAIRF
N/A
Verified
MAY 21, 2026
Methodology v1 · JAIRF v1.0.0
Powered by JAIRF v1.0.0 by Jentic · open methodology at /the-headless-index/methodology
Editorial verdict
Patronus AI is not built for machine consumption today. The Headless Index thesis-fit score of 25/100 fails the floor checks of the index, and JAIRF is recorded as N/A for this vendor because no public OpenAPI specification was reachable for the open-source scorer. In practice, vendors at this tier are not built for machine consumption today: agents can poke at them, but the dashboard remains the source of truth, and the rest of this verdict explains where Patronus AI lands inside that pattern.
On the API surface, the question is whether the API is the product or a layer beneath the dashboard. Patronus AI is LLM safety, evaluation, and hallucination detection for production. REST API for evaluators, datasets, experiments, and Lynx (hallucination detection). Python SDK is primary.[1] Schema observability is the related test: can an agent introspect the contract from cold, or does it have to read prose documentation to do so? REST documented at docs.patronus.ai. Schema discoverability is good.[2]
Driving this product through an agent is not realistic with the current surface: the API exists, but it is not the contract the vendor optimises for. On headless operability: On headless operability, the docs crawl did not produce topic coverage sufficient to score programmatic setup, billing, teams, schema, or CLI workflows. A targeted AI review pass should visit the vendor's docs index and confirm what programmatic surfaces actually exist.[3] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: No first-party Patronus MCP server. The product is downstream of agent stacks for evaluation.[4] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. On webhooks and events, the docs crawler did not locate a webhooks reference page or events catalog. Editorial review should confirm whether the vendor publishes events at all, and if so whether signing and replay are documented.
Net assessment: Patronus AI fails the floor checks of the methodology, with MCP posture[5] as the most acute gap. Any agent integration here will be brittle and short-lived until the vendor invests in machine-readable surfaces. Not currently suitable for agent consumption.
Verdict by Headless Index pipeline (auto)
// AI-drafted from the evidence layer. Editorial review pending.
Scores
Scorecard detail
Headless Index · 5 sub-criteria
API-first design intent5/20
scoredPatronus AI is LLM safety, evaluation, and hallucination detection for production. REST API for evaluators, datasets, experiments, and Lynx (hallucination detection). Python SDK is primary.
signals (4)
- +AI review appliedReviewer: Editorial review on 2026-05-20
- −OpenAPI specNot found across 34 probe paths
- ·GraphQL endpointDiscovered at https://www.patronus.ai/graphql, introspection disabled or scoped
- −SDKs maintainedNone detected in vendor org
cite (3)
- openapi.probes_tried@2026-05-21
- graphql.url@2026-05-21
- github.sdks@2026-05-21
Headless operationUnknown
UnknownEvaluators, custom rules, datasets, experiments, and Lynx scoring are programmable. The Patronus dashboard handles results review.
signals (9)
- +AI review appliedReviewer: Editorial review on 2026-05-20
- −API operations exposedNo OpenAPI spec; operations count unknown
- ·Docs pages crawled0 pages (crawler: none)
- ·Auth schemes documentedAuth documentation page not reached by crawler
- ·Setup / quickstart docsNot reached by crawler
- ·Billing docsNot reached by crawler
- ·Teams / org docsNot reached by crawler
- ·CLI docsNot reached by crawler
- ·Schema / data model docsNot reached by crawler
cite (8)
- openapi.operations_count@2026-05-21
- docs.pages_crawled@2026-05-21
- docs.pages_crawled@2026-05-21
- docs.topics_found.setup@2026-05-21
- docs.topics_found.billing@2026-05-21
- docs.topics_found.teams@2026-05-21
- docs.topics_found.cli@2026-05-21
- docs.topics_found.schema@2026-05-21
MCP & agent posture0/20
scoredNo first-party Patronus MCP server. The product is downstream of agent stacks for evaluation.
signals (4)
- +AI review appliedReviewer: Editorial review on 2026-05-20
- −Official MCP serverNone found in vendor's GitHub org or the official MCP registry
- −Community MCP serversNone found
- −Agent-friendly SDKsNo TypeScript/JavaScript SDK published (agents commonly run in TS/JS)
cite (3)
- mcp.registry_query@2026-05-21
- mcp.github_search_query@2026-05-21
- github.sdks@2026-05-21
Schema observability10/20
scoredREST documented at docs.patronus.ai. Schema discoverability is good.
signals (3)
- +AI review appliedReviewer: Editorial review on 2026-05-20
- −OpenAPINot discovered across 34 standard probe paths
- ·GraphQL introspectionGraphQL endpoint at https://www.patronus.ai/graphql but introspection is disabled, scoped, or behind authentication
cite (2)
- openapi.probes_tried@2026-05-21
- graphql.url@2026-05-21
Webhooks & eventsUnknown
UnknownEvaluator outcome webhooks for production monitoring. Catalog matches the LLM safety use case.
signals (2)
- +AI review appliedReviewer: Editorial review on 2026-05-20
- ·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.
cite (1)
- docs.pages_crawled@2026-05-21
JAIRF · 6 dimensions
JAIRF · N/A
This vendor does not publish a public OpenAPI specification. JAIRF cannot be computed. The Headless Index score and editorial verdict carry the readiness assessment.
No public OpenAPI specification discovered during collection
Powered by JAIRF v1.0.0 by Jentic
Band rationale:F band triggered: HeadlessIndex=25
04 / Embed
Show Patronus AI's score on your site.
Drop a live badge into your README, footer, or marketing page. It updates automatically when we re-score, and every embed is a dofollow link back here.