Play 91
Customer Churn Predictor
Multi-signal churn scoring with personalized retention campaigns.
Multi-signal churn scoring combining usage patterns, billing history, support interactions, network quality metrics, and competitive offers to predict churn risk and generate personalized retention campaigns. OpenAI generates retention messaging, Machine Learning builds churn models, Cosmos DB stores subscriber profiles, Communication Services delivers campaigns, and Functions orchestrate the scoring pipeline.
Architecture Pattern
Churn prediction pipeline: signal aggregation - risk scoring - segment analysis - retention campaign generation - delivery orchestration
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Churn Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (215 lines), evaluate (109 lines), tune (230 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI key input + envFile
TuneKit (AI Config)
- config/openai.json - retention messaging and churn analysis prompts
- config/churn.json - risk thresholds, offer budgets, signal weights
- config/guardrails.json - prediction accuracy minimums, budget caps
- evaluation/eval.py - Churn prediction AUC >0.85, Retention lift >15%
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.