Play 66
AI Infrastructure Optimizer
AI-driven cloud cost optimization with right-sizing, GPU analysis, and FinOps reporting.
Intelligent infrastructure optimization agent that queries Azure Resource Graph and Monitor to provide right-sizing recommendations, GPU utilization analysis, idle resource detection, and reserved instance purchase guidance. Generates auto-scaling policies, detects cost anomalies in real time, and produces monthly FinOps reports with actionable savings breakdowns. Uses Azure Advisor signals enriched with GPT analysis to explain optimization impact in business terms.
Architecture Pattern
FinOps analysis agent: resource graph queries, anomaly detection, savings reports
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — FinOps Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (232 lines), evaluate (112 lines), tune (164 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 — gpt-4o for optimization analysis
- config/guardrails.json — cost-optimization focus, savings validation
- evaluation/eval.py — Savings accuracy >85%, Adoption rate >60%
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.