https://www.m365.fm/entity/progressive-disclosure/Design pattern for AI agent skills in which only each skill's name and description stay in context, and the full instructions, scripts and resources load only when a request matches the skill.enhttps://www.m365.fm/community/u/mirko-p/blog/always-on-guidance-vs-situational-expertise-restructuring-your-ai-architecture/https://www.m365.fm/community/u/mirko-p/blog/always-on-guidance-vs-situational-expertise-restructuring-your-ai-architecture/Thu, 13 Aug 2026 08:52:39 -0000articleWelcome back to the blog companion for our podcast. In today's post, we are diving deep into a technical hurdle that almost every enterprise team hits after deployi…https://www.m365.fm/show/episodes/the-end-of-ai-bloat-why-modern-agents-need-skills/https://www.m365.fm/show/episodes/the-end-of-ai-bloat-why-modern-agents-need-skills/Sun, 26 Jul 2026 00:00:00 -0000episodeAI agents that start fast often become slow, costly and unreliable as their prompts grow into huge instruction blobs. This episode shows architects and Copilot Studio makers how modular skills, progressive disclosure and solid governance keep enterprise…https://www.m365.fm/show/episodes/the-end-of-prompting-how-to-build-the-copilot-agent-fabric/https://www.m365.fm/show/episodes/the-end-of-prompting-how-to-build-the-copilot-agent-fabric/Sun, 31 May 2026 00:00:00 -0000episodehe era of prompt engineering is ending. While organizations have spent years teaching employees how to write better AI prompts, this approach creates inconsistent results, limits scalability, and keeps humans trapped in every workflow step. Instead of relying…