https://www.m365.fm/entity/chunking/Chunking is the practice of splitting documents into smaller, coherent pieces before embedding and indexing them for retrieval, which strongly influences the precision of RAG answers.enhttps://www.m365.fm/community/u/mirko-p/blog/scaling-microsoft-copilot-to-35-million-pages-lessons-from-the-epstein-files/https://www.m365.fm/community/u/mirko-p/blog/scaling-microsoft-copilot-to-35-million-pages-lessons-from-the-epstein-files/Wed, 26 Aug 2026 16:14:20 -0000articleWelcome back to the podcast blog! Today, we are expanding on one of our most fascinating episodes yet. When data scales into the millions, traditional tools inevita…https://www.m365.fm/community/u/mirko-p/blog/scaling-microsoft-copilot-for-massive-datasets-lessons-from-35-million-pages/https://www.m365.fm/community/u/mirko-p/blog/scaling-microsoft-copilot-for-massive-datasets-lessons-from-35-million-pages/Wed, 26 Aug 2026 09:52:45 -0000articleWhen you are tasked with processing massive amounts of unstructured data, traditional search tools quickly hit a brick wall. In modern enterprise environments and c…https://www.m365.fm/community/u/mirko-p/blog/mastering-modular-architecture-in-microsoft-copilot-studio/https://www.m365.fm/community/u/mirko-p/blog/mastering-modular-architecture-in-microsoft-copilot-studio/Thu, 13 Aug 2026 14:23:17 -0000articleWelcome back to the blog companion for our podcast! When organizations begin their journey into enterprise artificial intelligence, they frequently hit a ceiling wh…https://www.m365.fm/community/u/mirko-p/blog/the-stateless-rag-trap-why-query-time-ai-architecture-falls-short/https://www.m365.fm/community/u/mirko-p/blog/the-stateless-rag-trap-why-query-time-ai-architecture-falls-short/Thu, 13 Aug 2026 07:51:49 -0000articleWelcome 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…https://www.m365.fm/community/u/mirko-p/blog/mastering-enterprise-rag-why-metadata-is-the-secret-to-better-ai-answers/https://www.m365.fm/community/u/mirko-p/blog/mastering-enterprise-rag-why-metadata-is-the-secret-to-better-ai-answers/Thu, 13 Aug 2026 07:49:07 -0000articleWelcome 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 …https://www.m365.fm/show/episodes/stop-leaking-data-how-to-run-local-llama-on-your-sharepoint-files/https://www.m365.fm/show/episodes/stop-leaking-data-how-to-run-local-llama-on-your-sharepoint-files/Thu, 18 Jun 2026 00:00:00 -0000episodeArtificial 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…https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/Mon, 08 Jun 2026 00:00:00 -0000episodeThe explosion of AI-powered applications has created a new challenge: how do you efficiently search through billions of vector embeddings without exploding infrastructure costs? In this episode, we explore the “billion-vector problem” and compare two leading…https://www.m365.fm/show/episodes/i-engineered-copilot-for-35-million-pages-the-epstein-files-challenge/https://www.m365.fm/show/episodes/i-engineered-copilot-for-35-million-pages-the-epstein-files-challenge/Sun, 07 Jun 2026 00:00:00 -0000episodeIn this episode, Mirko Peters explores one of the most ambitious experiments in enterprise AI: engineering Microsoft Copilot to analyze and reason across more than 35 million pages of highly complex and interconnected information, inspired by the scale and…https://www.m365.fm/show/episodes/building-private-rag-a-blueprint-for-sharepoint-n8n/https://www.m365.fm/show/episodes/building-private-rag-a-blueprint-for-sharepoint-n8n/Sat, 06 Jun 2026 00:00:00 -0000episodeIn 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…https://www.m365.fm/show/episodes/scaling-copilot-studio-in-the-enterprise-with-isha-kapoor-mvp/https://www.m365.fm/show/episodes/scaling-copilot-studio-in-the-enterprise-with-isha-kapoor-mvp/Mon, 01 Jun 2026 00:00:00 -0000episodeIn this episode of the M365.fm podcast, Mirko Peters sits down with Microsoft MVP Isha Kapoor to explore what it really takes to scale Microsoft Copilot Studio in large enterprise environments. The conversation moves beyond simple chatbot scenarios and…https://www.m365.fm/show/episodes/microsoft-cowork-iq-implementation-architecting-scalable-knowledge-graphs-for-modern-hybrid-workfor/https://www.m365.fm/show/episodes/microsoft-cowork-iq-implementation-architecting-scalable-knowledge-graphs-for-modern-hybrid-workfor/Fri, 29 May 2026 00:00:00 -0000episodeIn this episode of the Microsoft 365-focused podcast from m365.fm, the discussion explores how organizations can implement intelligent knowledge graph architectures to support modern hybrid work environments. The episode examines how Microsoft technologies…https://www.m365.fm/show/episodes/high-performance-agentic-workforce/https://www.m365.fm/show/episodes/high-performance-agentic-workforce/Mon, 09 Feb 2026 00:00:00 -0000episodeThis episode of the M365.FM Podcast (titled “How to Build a High-Performance Agentic Workforce in 30 Days”) explains why most enterprise AI agent programs fail quickly, and what it really takes to build an AI-driven workforce that delivers measurable business…