Play 67
AI Knowledge Management
Enterprise knowledge capture with freshness detection, gap analysis, and expert identification.
Enterprise knowledge management system that automatically ingests content from documents, wikis, emails, and meeting transcripts via Microsoft Graph. AI-powered freshness detection flags stale content, gap analysis identifies missing documentation, and expert identification connects questioners with subject-matter authorities. Features contextual Q&A powered by Azure AI Search and Semantic Kernel orchestration, with organizational memory that continuously learns.
Architecture Pattern
Multi-source RAG: freshness scoring, knowledge gap detection, expert routing
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Knowledge Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (224 lines), evaluate (110 lines), tune (182 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 Q&A, text-embedding-3-large for indexing
- config/guardrails.json — groundedness, relevance thresholds
- evaluation/eval.py — Retrieval precision >85%, Freshness coverage >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.