Play 09
AI Search Portal
Enterprise search with hybrid ranking and GPT synthesis.
A search experience that combines keyword matching with semantic understanding. AI Search handles the retrieval with custom scoring profiles, GPT-4o synthesizes results into readable summaries with citations. Web app frontend with faceted navigation, filters, and autocomplete.
Architecture Pattern
Hybrid search + GPT synthesis, scoring profiles
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — AI Search Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (128 lines), evaluate (100 lines), tune (104 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with AI Search admin key + envFile
TuneKit (AI Config)
- config/search.json — hybrid weights, semantic config, scoring profiles
- config/openai.json — synthesis prompts
- config/ranking.json — custom ranking rules
- evaluation/test-set.jsonl — search query samples
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.