Play 100
FAI Meta-Agent
The crown jewel — a self-orchestrating super-agent that builds agents.
The crown jewel — a self-orchestrating super-agent that understands user goals, selects and chains the appropriate FAI solution plays, provisions infrastructure, configures primitives, runs evaluation, and delivers production-ready AI systems. It is the FAI Protocol made autonomous — the agent that builds agents.
Architecture Pattern
Meta-agent orchestration: goal analysis - play selection - chain assembly - infrastructure provisioning - primitive configuration - evaluation - delivery
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Meta-Agent Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (283 lines), evaluate (126 lines), tune (227 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 - orchestration and play analysis prompts
- config/meta-agent.json - play selection strategy, chain depth, budget limits
- config/guardrails.json - evaluation pass thresholds, budget caps
- evaluation/eval.py - Play selection accuracy >95%, E2E success rate >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.