ENGINEERING NOTESThinking behind
Thinking behind
the systems.
Project decisions, lessons and practical notes from the work.
Building a Production Voice AI Pipeline: WhatsApp, Whisper, and Prompt Caching
Lessons from shipping a 24/7 WhatsApp voice pipeline with Whisper transcription, Claude generated replies, and the prompt caching setup that cut input token costs by roughly 90%.
Building a Human in the Loop Multi Agent Platform with LangGraph and MCP
How I designed an agent platform on LangGraph's StateGraph with Model Context Protocol tool access, persistent checkpointed memory, and human approval steps before sensitive actions.
RAG vs Fine tuning: When to Use Which
A practical breakdown of when RAG outperforms fine tuning and vice versa, based on real production experience building both types of systems.
Building an Enterprise Legal AI Platform with RAG
How I architected a production RAG system processing 50,000+ French legal documents with document ingestion, hybrid search, Claude and Pinecone.