Play 40
Copilot Studio Advanced
Enterprise Copilot — declarative agents, TypeSpec, API plugins, M365 SSO, Graph API.
Enterprise-grade Microsoft Copilot Studio extensions featuring declarative agents with TypeSpec definitions, API plugins for custom actions, adaptive cards for rich responses, multi-turn conversation state management, enterprise SSO via Entra ID, and deep M365 data integration via Graph API. Copilot Studio provides the canvas, Azure OpenAI powers the intelligence, Dataverse stores domain data, and Power Platform enables workflow automation.
Architecture Pattern
Enterprise Copilot: TypeSpec agents, API plugins, M365 SSO, Graph data, adaptive cards
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Copilot Studio Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (289 lines), evaluate (198 lines), tune (290 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Power Platform + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — model selection for copilot
- config/copilot.json — agent config, permissions, scoping
- config/guardrails.json — content safety, data access controls
- evaluation/eval.py — Agent accuracy >85%, User satisfaction >80%
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.