Play 91
Customer Churn Predictor
High✅ Ready
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
Azure OpenAIAzure Machine LearningAzure Cosmos DBAzure Communication ServicesAzure Functions
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
Churn risk thresholdRetention offer budgetSignal decay weightsCampaign channel mixWin-back eligibility window
Estimated Cost
Dev/Test
$80-200/mo
Production
$2K-8K/mo