Play 56
Semantic Code Search
Natural language codebase search with intent-based function discovery.
Natural language code search engine that understands code semantics beyond keyword matching. Indexes repositories into Azure AI Search with code-specific embeddings for intent-based function discovery and cross-repo navigation. Features dependency mapping, automated code documentation generation, and MCP tool integration for IDE-native search experiences.
Architecture Pattern
Code-aware RAG: specialized embeddings, cross-repo semantic indexing
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Code Search Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (251 lines), evaluate (126 lines), tune (191 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + AI Search inputs + envFile
TuneKit (AI Config)
- config/openai.json — embedding model, search relevance
- config/guardrails.json — result quality, freshness thresholds
- evaluation/eval.py — MRR >0.75, Query latency <200ms
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.