Play 88
Visual Product Search
Image-based product discovery with visual similarity and virtual try-on.
Image-based product discovery combining reverse image search, visual similarity matching, style recommendations, and virtual try-on capabilities for fashion, furniture, and home decor retailers. AI Vision extracts visual features, OpenAI generates style descriptions and recommendations, AI Search indexes product embeddings, Container Apps serve the search API, and Cosmos DB stores product catalog and user preferences.
Architecture Pattern
Visual search pipeline: image upload - feature extraction - similarity matching - style recommendation - virtual try-on - product results
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Visual Search Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (211 lines), evaluate (128 lines), tune (242 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 - style description and recommendation prompts
- config/vision.json - similarity thresholds, catalog refresh, rendering quality
- config/guardrails.json - content moderation, result diversity thresholds
- evaluation/eval.py - Search relevance >85%, Try-on quality >80%
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.