Case Study 02
FlowSight AI
Multi-agent AI consulting & workflow automation platform
May 2026
PythonLangGraphClaude APIHugging FaceChromaFastAPISupabasePostgreSQLNext.jsTailwindCSSLangSmith
Automates end-to-end consulting — analysis, research, strategy, solution architecture, ROI modeling, risk & governance, executive reporting — via a 7-agent LangGraph pipeline.
flowsight.ai/dashboard

What I did
4- 01
Automates end-to-end consulting — analysis, research, strategy, solution architecture, ROI modeling, risk & governance, executive reporting — via a 7-agent LangGraph pipeline.
- 02
Grounds every recommendation in the client's own policies through cited RAG (Hugging Face Qwen3 embeddings + Chroma), producing audit-ready, traceable deliverables.
- 03
Cut analysis turnaround ~60% (5+ min → ~2 min) with cost-optimized model tiering (Claude Haiku for analytics, Sonnet for synthesis).
- 04
50+ test suite with dependency-injected fakes for zero-cost, key-free CI; LangSmith tracing + evaluation for quality.
Tech stack
PythonLangGraphClaude APIHugging FaceChromaFastAPISupabasePostgreSQLNext.jsTailwindCSSLangSmith
More projects