Play 45
Real-Time Event AI
Streaming AI for sub-second inference on fraud, IoT anomalies, and live sentiment.
Streaming AI pipeline for continuous event processing — fraud alerts, IoT anomalies, live sentiment, supply chain disruptions with sub-second inference, windowed aggregation, and real-time WebSocket dashboards. Powered by Event Hubs for high-throughput ingestion, Cosmos DB for state management, and SignalR for live push to dashboards. Scales to millions of events per second.
Architecture Pattern
Event-driven streaming: windowed aggregation, AI inference, real-time WebSocket push
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Event AI Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (260 lines), evaluate (166 lines), tune (231 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Event Hubs + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — gpt-4o for enrichment
- config/streaming.json — window sizes, aggregation rules, SLAs
- config/guardrails.json — rate limiting, data validation
- evaluation/eval.py — p99 latency <500ms, Detection accuracy >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.