<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Manan Chawda</title><description>Writing about distributed systems rigor applied to AI — and the things I got wrong the first time.</description><link>https://mananchawda.com/</link><language>en-us</language><item><title>Multi-Agent RAG with LangGraph: when 4 agents beat 1</title><link>https://mananchawda.com/writing/multi-agent-rag-langgraph/</link><guid isPermaLink="true">https://mananchawda.com/writing/multi-agent-rag-langgraph/</guid><description>Building a production retrieval-augmented system with router, retriever, verifier, and synthesizer agents — and what changed when we added RAGAS evaluation.</description><pubDate>Sun, 15 Mar 2026 00:00:00 GMT</pubDate><category>RAG</category><category>LangGraph</category><category>AI Infrastructure</category><category>Production AI</category></item></channel></rss>