I'm Tech Lead of AI Efficiency at Petlove, where my team builds a conversational AI agent for customer support. Before that I led Growth engineering across the e-commerce funnel. I've spent 7+ years building web products with TypeScript, Vue, and Nuxt, and now I apply that same engineering discipline to AI: agents, LangGraph, and evals.
I built a fully conversational post-sales chatbot with LangChain and LangGraph, where a decision model picks the subagent on every message. Architecture, code, fallback, A/B, and the failures that showed up.
I had Microsoft-Decision-1 pick the subagent and LLM in a post-sales chatbot: harness, calibration, cost guard, and what 1,000 synthetic conversations showed.
How to structure a React SPA in vertical slices by domain: public API per slice, data from route loaders, and an architecture test that blocks shortcuts in CI.
How an LLM base model becomes ChatGPT: supervised fine-tuning, tool use, hallucination reduction and reinforcement learning explained clearly and in depth.