Play 85
Policy Impact Analyzer
Regulatory change detection with cross-sector impact assessment.
Regulatory change detection with cross-sector impact assessment, stakeholder mapping, public comment analysis, and automated briefing generation for legislative and executive decision-makers. OpenAI analyzes policy text and generates briefings, AI Search indexes regulatory databases, Document Intelligence extracts structured data from legislative documents, Cosmos DB stores impact assessments, and Functions orchestrate change detection pipelines.
Architecture Pattern
Policy analysis pipeline: regulatory feed monitoring - document extraction - impact assessment - stakeholder mapping - briefing generation
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Policy Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (231 lines), evaluate (107 lines), tune (245 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + AI Search inputs + envFile
TuneKit (AI Config)
- config/openai.json - policy analysis and briefing generation prompts
- config/regulatory.json - source feeds, impact categories, stakeholder types
- config/guardrails.json - bias detection, factual accuracy thresholds
- evaluation/eval.py - Impact accuracy >85%, Briefing quality >90%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.