Designing and shipping multi-agent, multi-turn conversational pipelines for real-world banking & financial workflows. Deeply interested in the infrastructure layer of agentic AI — memory, observability, context engineering, and evals.
AG-UI protocol · MCP · AI evals · Memory architecture · Voice AI agents
| Project | Description |
|---|---|
| GenerativeUI | Agentic onboarding with LangGraph + Chainlit — backend drives dynamic form generation via structured LLM outputs |
| AgenticClassification | Multi-step text analysis pipeline with LangGraph |
| LearnDocker | Sentiment analysis model → FastAPI → Docker |
| what2eat | Vegan recipe recommender system |