Play 55
Supply Chain AI
Demand forecasting, inventory optimization, and disruption alerts.
AI-powered supply chain management platform for demand forecasting, inventory optimization, and supplier risk assessment. Combines Azure ML for time-series predictions with OpenAI for natural language scenario modeling. Features route optimization, real-time disruption alerts via Event Hubs, and what-if scenario modeling for supply chain resilience planning.
Architecture Pattern
Event-driven forecasting: ML predictions + agent-based scenario modeling
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Supply Chain Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (236 lines), evaluate (122 lines), tune (192 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + ADX cluster inputs + envFile
TuneKit (AI Config)
- config/openai.json — scenario generation, risk analysis
- config/guardrails.json — forecast confidence, alert thresholds
- evaluation/eval.py — Forecast MAPE <15%, Alert precision >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.