<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Retrieval-augmented generation (RAG) – M365.FM</title><link>https://www.m365.fm/entity/rag/</link><description>A pattern in which an AI model first retrieves relevant documents from a knowledge source and then writes its answer based on them. It reduces made-up answers and lets models use current, private data without retraining.</description><language>en</language><item><title>Why Private RAG Isn't Enough: Bridging Data Sovereignty and Security</title><link>https://www.m365.fm/community/u/mirko-p/blog/why-private-rag-isnt-enough-bridging-data-sovereignty-and-security/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/why-private-rag-isnt-enough-bridging-data-sovereignty-and-security/</guid><pubDate>Fri, 28 Aug 2026 03:36:51 -0000</pubDate><category>article</category><description>Welcome back to the blog! In today's post, we are expanding on a crucial conversation we recently tackled on the podcast. If you manage data or build AI systems wit…</description></item><item><title>Mastering Azure AI Search: Beyond Traditional Keyword Matching</title><link>https://www.m365.fm/community/u/mirko-p/blog/mastering-azure-ai-search-beyond-traditional-keyword-matching/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/mastering-azure-ai-search-beyond-traditional-keyword-matching/</guid><pubDate>Thu, 27 Aug 2026 06:39:00 -0000</pubDate><category>article</category><description>Welcome to our deep dive into the world of cloud-based discovery and retrieval systems. If you have ever typed a query into a company intranet, e-commerce site, or …</description></item><item><title>Structuring SharePoint Libraries for AI-Powered Retrieval</title><link>https://www.m365.fm/community/u/mirko-p/blog/structuring-sharepoint-libraries-for-ai-powered-retrieval/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/structuring-sharepoint-libraries-for-ai-powered-retrieval/</guid><pubDate>Wed, 26 Aug 2026 16:18:07 -0000</pubDate><category>article</category><description>Welcome to our deep dive into organizing your enterprise content for artificial intelligence. As organizations race to implement generative AI, a common bottleneck …</description></item><item><title>Structuring SharePoint for Maximum AI Retrieval Accuracy</title><link>https://www.m365.fm/community/u/mirko-p/blog/structuring-sharepoint-for-maximum-ai-retrieval-accuracy/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/structuring-sharepoint-for-maximum-ai-retrieval-accuracy/</guid><pubDate>Wed, 26 Aug 2026 09:53:13 -0000</pubDate><category>article</category><description>When organizations rush into implementing artificial intelligence initiatives, they often overlook the foundation upon which those systems rely: the document reposi…</description></item><item><title>Treating Every Business Document as Executable Code: Rethinking Enterprise AI Security</title><link>https://www.m365.fm/community/u/mirko-p/blog/treating-every-business-document-as-executable-code-rethinking-enterprise-ai-security/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/treating-every-business-document-as-executable-code-rethinking-enterprise-ai-security/</guid><pubDate>Wed, 26 Aug 2026 09:49:12 -0000</pubDate><category>article</category><description>Welcome back to the podcast companion blog. As artificial intelligence becomes deeply integrated into our daily workflows, we tend to view everyday business tools&amp;m…</description></item><item><title>The Stateless RAG Trap: Why Query-Time AI Architecture Falls Short</title><link>https://www.m365.fm/community/u/mirko-p/blog/the-stateless-rag-trap-why-query-time-ai-architecture-falls-short/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/the-stateless-rag-trap-why-query-time-ai-architecture-falls-short/</guid><pubDate>Thu, 13 Aug 2026 07:51:49 -0000</pubDate><category>article</category><description>Welcome back to the blog! If you have been following along with our podcast discussions on enterprise artificial intelligence, you know we spend a lot of time looki…</description></item><item><title>Mastering Enterprise RAG: Why Metadata is the Secret to Better AI Answers</title><link>https://www.m365.fm/community/u/mirko-p/blog/mastering-enterprise-rag-why-metadata-is-the-secret-to-better-ai-answers/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/mastering-enterprise-rag-why-metadata-is-the-secret-to-better-ai-answers/</guid><pubDate>Thu, 13 Aug 2026 07:49:07 -0000</pubDate><category>article</category><description>Welcome back to the blog! If you have ever built a quick proof-of-concept AI chatbot, you know how magical it feels. You upload a few PDFs, point a vector database …</description></item><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>Beyond Retrieval: Implementing LLM Wikis and Advanced Memory Layers for Enterprise AI</title><link>https://www.m365.fm/community/u/mirko-p/blog/beyond-retrieval-implementing-llm-wikis-and-advanced-memory-layers-for-enterprise-ai/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/beyond-retrieval-implementing-llm-wikis-and-advanced-memory-layers-for-enterprise-ai/</guid><pubDate>Tue, 11 Aug 2026 13:22:05 -0000</pubDate><category>article</category><description>Welcome back to the podcast and our companion blog! Today, we are diving deep into a topic that has been dominating architectural whiteboards across the enterprise …</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><item><title>Your Copilot Has No Memory — Why RAG Fails and LLM Wiki Fixes It</title><link>https://www.m365.fm/show/episodes/your-copilot-has-no-memory-why-rag-fails-and-llm-wiki-fixes-it/</link><guid>https://www.m365.fm/show/episodes/your-copilot-has-no-memory-why-rag-fails-and-llm-wiki-fixes-it/</guid><pubDate>Mon, 10 Aug 2026 00:00:00 -0000</pubDate><category>episode</category><description>Copilot can answer a question perfectly today and fumble the same question tomorrow because it searches instead of remembering. This episode explains why RAG-based Copilot stays shallow and how the LLM Wiki pattern adds compiled, maintained knowledge, for IT…</description></item><item><title>RAG on Azure — Simply Explained</title><link>https://www.m365.fm/show/episodes/rag-on-azure-simply-explained/</link><guid>https://www.m365.fm/show/episodes/rag-on-azure-simply-explained/</guid><pubDate>Thu, 16 Jul 2026 00:00:00 -0000</pubDate><category>episode</category><description>Retrieval-Augmented Generation (RAG) is one of the most important techniques behind modern AI applications, enabling large language models to answer questions using your own business data instead of relying only on their training knowledge. In this episode of…</description></item><item><title>Private RAG Security: Authorization-Aware Data Retrieval</title><link>https://www.m365.fm/show/episodes/private-rag-isnt-enough-the-missing-layer-between-data-sovereignty-and-data-security/</link><guid>https://www.m365.fm/show/episodes/private-rag-isnt-enough-the-missing-layer-between-data-sovereignty-and-data-security/</guid><pubDate>Sat, 20 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>veryone is talking about Private RAG, sovereign AI, regional hosting, and keeping enterprise data inside controlled environments. But in this episode of M365 FM, Mirko Peters explores a critical security gap that many organizations overlook: data sovereignty…</description></item><item><title>How to Run Local Llama on SharePoint Files Securely</title><link>https://www.m365.fm/show/episodes/stop-leaking-data-how-to-run-local-llama-on-your-sharepoint-files/</link><guid>https://www.m365.fm/show/episodes/stop-leaking-data-how-to-run-local-llama-on-your-sharepoint-files/</guid><pubDate>Thu, 18 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>Artificial Intelligence is transforming the way organizations manage knowledge, documents, and collaboration. Yet as companies rush to adopt AI assistants and large language models, one question continues to dominate every conversation: how can you benefit…</description></item><item><title>Indirect Prompt Injection Security for Enterprise AI</title><link>https://www.m365.fm/show/episodes/indirect-injection-the-silent-killer-of-enterprise-ai/</link><guid>https://www.m365.fm/show/episodes/indirect-injection-the-silent-killer-of-enterprise-ai/</guid><pubDate>Tue, 16 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>Most organizations believe hallucinations are the biggest risk in enterprise AI. In reality, one of the most dangerous threats is something far less visible: Indirect Prompt Injection. In this episode, we explore how trusted documents, emails, SharePoint…</description></item><item><title>How to Build Private RAG with SharePoint and n8n</title><link>https://www.m365.fm/show/episodes/building-private-rag-a-blueprint-for-sharepoint-n8n/</link><guid>https://www.m365.fm/show/episodes/building-private-rag-a-blueprint-for-sharepoint-n8n/</guid><pubDate>Sat, 06 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>In this episode of M365.fm, Mirko Peters explores how organizations can build a secure and private Retrieval-Augmented Generation (RAG) platform using SharePoint as the knowledge source and n8n as the orchestration layer. The discussion focuses on moving…</description></item><item><title>When to Use RAG vs Microsoft 365 Copilot</title><link>https://www.m365.fm/show/episodes/rag-vs-microsoft-copilot-when-to-use-which/</link><guid>https://www.m365.fm/show/episodes/rag-vs-microsoft-copilot-when-to-use-which/</guid><pubDate>Fri, 05 Dec 2025 00:00:00 -0000</pubDate><category>episode</category><description>The night is thick with static inside your tenant, and the questions aren’t small anymore. Copilot can walk the clean, well-lit M365 streets — summarizing inbox noise, tightening your notes, finding what you already have permission to see. Fast, friendly…</description></item><item><title>Build Traceable Copilots with Agentic RAG on Azure</title><link>https://www.m365.fm/show/episodes/stop-building-dumb-copilots-agentic-rag-fix/</link><guid>https://www.m365.fm/show/episodes/stop-building-dumb-copilots-agentic-rag-fix/</guid><pubDate>Mon, 17 Nov 2025 00:00:00 -0000</pubDate><category>episode</category><description>Your Copilot isn’t smart – it’s a very expensive autocomplete. In this episode, we break down why classic RAG (retrieve-augment-generate) quietly fails the moment your truth lives in more than one system, and how “agentic RAG” on Azure turns Copilot from a…</description></item><item><title>Build Hands-Free Copilot Voice Experiences with GPT-4o</title><link>https://www.m365.fm/show/episodes/voice-driven-copilot-integration-benefits/</link><guid>https://www.m365.fm/show/episodes/voice-driven-copilot-integration-benefits/</guid><pubDate>Sun, 16 Nov 2025 00:00:00 -0000</pubDate><category>episode</category><description>Typing to Copilot is the new fax machine—and your thumbs are the bottleneck. In this episode we break down how to give Copilot an actual voice, a memory, and a legal department, so it can keep up with the way you think, not the way you type. You’ll hear how…</description></item><item><title>Fix Common Azure AI Foundry Project Failures</title><link>https://www.m365.fm/show/episodes/the-azure-ai-foundry-trap-why-most-fail-fast/</link><guid>https://www.m365.fm/show/episodes/the-azure-ai-foundry-trap-why-most-fail-fast/</guid><pubDate>Mon, 03 Nov 2025 00:00:00 -0000</pubDate><category>episode</category><description>In this episode we walk through what really happens when Azure AI Foundry doesn’t behave the way you expect, especially when the Agent Service or deployments start acting up. Azure AI Foundry is supposed to feel smooth, almost invisible, tying together OpenAI…</description></item><item><title>Copilot Studio vs Azure AI Foundry: Which Should You Use?</title><link>https://www.m365.fm/show/episodes/copilot-studio-vs-azure-ai-foundry-pick-your-poison/</link><guid>https://www.m365.fm/show/episodes/copilot-studio-vs-azure-ai-foundry-pick-your-poison/</guid><pubDate>Mon, 03 Nov 2025 00:00:00 -0000</pubDate><category>episode</category><description>In this episode, we unpack two major AI platforms in the Microsoft ecosystem—Copilot Studio and Azure AI Foundry—and help listeners understand when to use each one. Whether you're building conversational AI, custom machine learning models, or enterprise-grade…</description></item></channel></rss>