Play 72
Climate Risk Assessor
Climate scenario modeling for financial risk and insurance underwriting.
Climate scenario modeling for financial institutions and insurance companies. Analyzes physical risk (flooding, wildfire, sea level rise), transition risk (carbon pricing, regulatory changes), and liability risk (litigation exposure). Azure ML runs climate projection models, AI Search retrieves regulatory and scientific data, and OpenAI generates explainable risk assessments with confidence intervals for board-level reporting.
Architecture Pattern
RAG + ML climate modeling: scenario projection → risk scoring → explainable assessment
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Climate Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (199 lines), evaluate (123 lines), tune (237 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + NGFS API inputs + envFile
TuneKit (AI Config)
- config/openai.json — risk analysis and explanation prompts
- config/climate.json — scenario parameters, risk models, time horizons
- config/guardrails.json — confidence intervals, data provenance
- evaluation/eval.py — Risk accuracy >85%, Scenario coverage >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.