Play 53
Legal Document AI
Contract review, clause extraction, and risk identification with audit trails.
Legal document analysis agent for contract review, clause extraction, risk identification, and compliance checking. Uses RAG architecture with Azure AI Search over legal document corpus with privilege detection and redline comparison. Maintains full audit trails in Cosmos DB for regulatory compliance. Employs deterministic validation for high-stakes legal conclusions.
Architecture Pattern
RAG + deterministic validation: high-stakes legal analysis with audit logging
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Legal AI Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (223 lines), evaluate (124 lines), tune (188 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + Doc Intelligence inputs + envFile
TuneKit (AI Config)
- config/openai.json — low temperature for precise legal analysis
- config/guardrails.json — high groundedness, privilege detection
- evaluation/eval.py — Clause accuracy >90%, Risk recall >85%
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.