Play 67
AI Knowledge Management
High✅ Ready
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
Azure OpenAIAzure AI SearchCosmos DBBlob StorageAzure FunctionsMicrosoft Graph
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
Freshness decay rateChunk overlap tokensExpert match thresholdGap detection sensitivityEmbedding model
Estimated Cost
Dev/Test
$80–180/mo
Production
$2K–8K/mo