{"data":{"slug":"agent-role","term":"Agent Role","bucket":"agents","definition":"A specialist persona inside a Build Room session: product_wedge, build_plan, eval_benchmark, gtm_interviews, moat_risk.","short_definition":"A specialist persona inside a Build Room session: product_wedge, build_plan, eval_benchmark, gtm_interviews, moat_risk.","long_definition":"Agent Role is the persona contract used by Build Room. Each role produces a typed artifact (PRD outline, MVP plan, evaluation plan, outreach packet, risk matrix) and runs against the same paper context. The role specs live alongside the Build Room service so a downstream consumer can introspect what each role does without reading any code.","related_terms":["build-room","build-loop","artifact-type"],"related_term_routes":[{"slug":"build-room","term":"Build Room","route":"/resources/glossary/build-room"},{"slug":"build-loop","term":"Build Loop","route":"/resources/glossary/build-loop"},{"slug":"artifact-type","term":"Artifact Type","route":"/resources/glossary/artifact-type"}],"canonical_route":"/resources/glossary/agent-role","api_route":"/api/v1/resources/glossary/agent-role","jsonld_id":"https://sciencetostartup.com/resources/glossary/agent-role","variants":[],"tldr":"A specialist persona inside a Build Room session: product_wedge, build_plan, eval_benchmark, gtm_interviews, moat_risk.","key_points":[],"quality_tier":null,"citation_count":null,"source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","definition_sections":{"schema_version":1,"intro":"Agent Role is the persona contract used by Build Room. Each role produces a typed artifact (PRD outline, MVP plan, evaluation plan, outreach packet, risk matrix) and runs against the same paper context. The role specs live alongside the Build Room service so a downstream consumer can introspect what each role does without reading any code.","sections":[{"title":"Definition","items":[{"subtitle":"Agent Role","text":"Agent Role is the persona contract used by Build Room. Each role produces a typed artifact (PRD outline, MVP plan, evaluation plan, outreach packet, risk matrix) and runs against the same paper context. The role specs live alongside the Build Room service so a downstream consumer can introspect what each role does without reading any code."}]},{"title":"Related vocabulary","items":[{"subtitle":"Build Room","text":"An agent-orchestrated session in Build Loop. Multiple specialist agents (wedge, plan, eval, GTM, moat) produce startup artifacts."},{"subtitle":"Build Loop","text":"The build/watch/verify decision surface. Where Signal Canvas asks what is interesting, Build Loop asks should you build it."},{"subtitle":"Artifact Type","text":"The output type of a Build Room agent: prd_outline, mvp_plan, evaluation_plan, outreach_packet, risk_matrix."}]}],"cited_arxiv_ids":[]}},"meta":{"canonical_route":"/resources/glossary/agent-role","api_route":"/api/v1/resources/glossary/agent-role","source":{"label":"curated glossary catalog","source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","method_version":"public_glossary_curated_terms_v2","freshness":{"status":"versioned","observed_at":null,"fresh_until":null,"reason":"Git-versioned curated catalog; daily ingestion freshness windows do not apply.","reason_code":"git_versioned_curated_catalog"},"source_count":111,"bucket_count":7,"buckets":["scoring","surfaces","agents","distribution","data","foresight","buildability"]}}}