Play 09
AI Search Portal
Medium🔧 Skeleton
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
AI Search (semantic)Azure OpenAI (gpt-4o)App Service (B1)Blob Storage
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
Hybrid weights (keyword vs semantic)Scoring profilesSynthesis promptsResult countFacet configuration
Estimated Cost
Dev/Test
$100–250/mo
Production
$1.2K–5K/mo