Pangram verdict · v3.3
We believe that this entire text is AI.
AI likelihood · overall
AIArticle text · 411 words · 1 segments analyzed
v0.1 Draft SpecificationThe open standard for|OJCP defines how AI agents discover, reason over, and act on job opportunities. Built on MCP. Interoperable with schema.org. Governed by an independent steering committee, and designed to compose with the broader agentic web.Why OJCPBuilt for the agentic webA shared protocol so AI agents and job providers speak the same language — structured, discoverable, privacy-respecting.MCP-Native ToolsOJCP tools are valid MCP tools. Any MCP client can call search_jobs, get_job_detail, and begin_application out of the box.Structured DiscoveryProviders expose a manifest at /.well-known/ojcp.json. Agents discover capabilities, tools, and apply paths automatically.Normalized Apply PathsA standard taxonomy of application mechanisms — from ATS-direct to agent-ready flows — so agents know exactly how to apply.Consent-First PrivacyCandidate data is opt-in and scoped. Resume embeddings enable fit-scoring without transmitting PII. Agents self-declare identity.Agent-Aware RankingPass CandidateContext for personalized results. Providers return fit_score and fit_rationale alongside standard job data.WebMCP ReadyBrowser-native agents can access OJCP tools via navigator.modelContext. Same schemas, same tools, new surface.SpecificationSchemas & ToolsOJCP defines seven core schemas and six standard MCP tools. Providers MUST implement search_jobs; all others are recommended. Custom tools use namespaced names (e.g., acme:get_referral_link).MCP ToolsDiscovery endpoint at /.well-known/ojcp.jsonojcp_versionprovidertoolsmcp_endpointauthrate_limitsExtends schema.org/JobPosting with agent-specific fieldsojcp_idskills_requiredexperienceLevelapply_pathsurgencyConsent-scoped candidate profile for personalized resultsconsent_scopeskillsexperience_yearsemployment_type_preferenceAgent self-identification for audit trailsagent_idacting_on_behalf_ofinteraction_modeuser_consent_tokenIdentity verification action for human completionstep_idtypeverifier_idverification_urlhuman_requiredJWS proof with required claims: iss, aud, sub, iat, exp, nonce — no PIIstep_idverifier_idproof_token (JWS)subject_hash (SHA-256)issued_atexpires_atDiscovery document hosted at /.well-known/ojcp-verifier.jsonverifier_idverification_typesproof_delivery_methodsproof_format (jws|jws+jwe)signing_algorithmspublic_keys_url (JWKS)How It WorksFour steps from discovery to applicationDiscoverAgent probes /.well-known/ojcp.json or queries the OJCP Registry to find providers. The manifest declares available tools, apply paths, and authentication requirements.Search & EvaluateAgent calls search_jobs with optional candidate_context for personalized ranking. Each result includes fit_score, apply paths, and structured metadata.ApplyAgent calls begin_application with an agent_declaration and the candidate's consent token. The provider returns required fields and a session for multi-step flows.TrackAgent calls check_application_status to monitor progress. Providers emit structured status updates throughout the hiring pipeline.ExamplesSee it in actionFrom discovery to application — real OJCP payloads your agents can use today.→ /.well-known/ojcp.jsonApply PathsNormalized application taxonomyOJCP standardizes the fragmented landscape of application mechanisms into a taxonomy agents can reason over.TypeDescriptionAgent Submissionats_directApply directly via ATS (Workday, Greenhouse, Lever, etc.)Variesprovider_hostedProvider controls the apply flow and delivers to ATSFull Supportplatform_nativeThird-party platform owns the flow (e.g., Indeed Apply, Easy Apply)LimitedemailLegacy email-based applicationNot Supportedexternal_redirectRedirect to opaque external pageNot SupportedcustomCatch-all for non-standard apply mechanisms (homegrown, conversational, etc.)VariesLive PlaygroundTry the OJCP APIThis site is a live OJCP provider. Fire real tool calls against mock data — the same endpoint MCP clients connect to.MCP: /api/mcpManifest: /.well-known/ojcp.jsonQueryRemote OKMin Salary