Play 60
Responsible AI Dashboard
Enterprise RAI governance with fairness metrics and EU AI Act compliance.
Enterprise responsible AI governance platform tracking model fairness metrics, bias detection across demographics, and transparency reports. Features automated explanation generation, content safety monitoring, and EU AI Act compliance tracking. Built on Azure ML for model evaluation, Azure Monitor for real-time safety signals, and Static Web Apps dashboard for executive visibility.
Architecture Pattern
Observability dashboard: ML-powered fairness evaluation, compliance automation
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — RAI Dashboard Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (258 lines), evaluate (117 lines), tune (194 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + App Insights inputs + envFile
TuneKit (AI Config)
- config/openai.json — explanation generation, report summarization
- config/guardrails.json — fairness thresholds, safety baselines
- evaluation/eval.py — Fairness disparity <5%, Safety incident rate 0%
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.