<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>ReAct pattern – M365.FM</title><link>https://www.m365.fm/entity/react-pattern/</link><description>An agent reasoning pattern that alternates between reasoning about what is needed and acting, for example retrieving data or calling a tool, until the model decides it has enough to answer.</description><language>en</language><item><title>Cost and Latency Trade-Offs in Agentic RAG vs Traditional Retrieval</title><link>https://www.m365.fm/community/u/mirko-p/blog/cost-latency-trade-offs-agentic-rag-vs-traditional-retrieval/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/cost-latency-trade-offs-agentic-rag-vs-traditional-retrieval/</guid><pubDate>Tue, 11 Aug 2026 19:05:38 -0000</pubDate><category>article</category><description>Discover why Agentic RAG is 2-10x more expensive and slower than traditional RAG, and learn how to choose the right architecture for your enterprise AI.</description></item><item><title>The Copilot Assumption That's Holding You Back — Agentic RAG</title><link>https://www.m365.fm/show/episodes/agentic-rag/</link><guid>https://www.m365.fm/show/episodes/agentic-rag/</guid><pubDate>Tue, 11 Aug 2026 00:00:00 -0000</pubDate><category>episode</category><description>Many teams still treat Copilot as a search box and blame the tool when answers come back incomplete. This episode explains agentic RAG, the orchestration loop behind modern Copilot, for IT decision makers and Microsoft 365 architects. You learn when agentic…</description></item></channel></rss>