{"podcast":{"title":"M365.FM a Microsoft MVP Podcast by Mirko Peters","slug":"m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214","podcast_index_feed_id":7311214,"rss_url":"https://www.spreaker.com/show/6704921/episodes/feed","website_url":"https://www.m365.fm","image_url":"https://d3wo5wojvuv7l.cloudfront.net/t_rss_itunes_square_1400/images.spreaker.com/original/dcd2a8cc504197846a71af23bbeb0707.jpg","author":"Mirko Peters - Microsoft 365, Teams, SharePoint, and Copilot for IT Pros","episode_count":989,"summary":"M365.FM is a podcast about Microsoft 365, Microsoft Copilot, AI, Modern Work, security, governance, Power Platform, Azure, and the technologies shaping the future of work.Hosted by Microsoft MVP Mirko Peters, M365.FM brings together Microsoft MVPs, Microsoft employees, product experts, architects, developers, and community leaders from around the world.Each episode goes beyond announcements and hype to explore what Microsoft technologies mean in practice. From Microsoft 365 Copilot and AI agents to Teams, SharePoint, Power Platform, Microsoft Fabric, Entra, Purview, security, governance, adoption, and automation, M365.FM focuses on real-world experience, implementation, strategy, and lessons learned.Expect expert interviews, technical deep dives, practical explainers, and conversations with people building, implementing, and shaping the Microsoft ecosystem.If you work with Microsoft 365, Copilot, AI, Modern Work, or the Microsoft Cloud, M365.FM helps you understand what matters, what works, and what is coming next.Hosted by Mirko Peters, Microsoft MVP. Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-a-microsoft-mvp-podcast-by-mirko-peters--6704921/supp…","last_synced_at":"2026-09-17T20:22:41.104701+00:00","page_url":"https://stenobird.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214"},"episode":{"title":"The End of AI Bloat: Why Modern Agents Need Skills","slug":"the-end-of-ai-bloat-why-modern-agents-need-skills","published_at":"2026-07-26T13:00:03+00:00","page_url":"https://stenobird.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/the-end-of-ai-bloat-why-modern-agents-need-skills","show_page_url":"https://stenobird.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214","url":"https://www.spreaker.com/episode/the-end-of-ai-bloat-why-modern-agents-need-skills--73164010","audio_url":"https://dts.podtrac.com/redirect.mp3/api.spreaker.com/download/episode/73164010/the_end_of_ai_bloat_why_modern_agents_need_skills.mp3","summary":"Many AI agents start out fast, responsive, and surprisingly intelligent. But after a few months of real-world use, something changes. Response times increase, costs rise, prompts become enormous, and accuracy begins to decline. Organizations often respond by upgrading to larger models, expanding prompts, or adding more orchestration—but the underlying problem remains. The issue isn't the model. It's the architecture. This episode explains why monolithic prompts create what is known as the Context Tax, how modular Skills solve the problem through progressive disclosure, and why Skills are becoming the architectural foundation of modern AI agents across Microsoft Copilot Studio, GitHub Copilot, Claude Code, and the broader enterprise AI ecosystem. THE CONTEXT TAX Every enterprise AI project eventually faces the same challenge. At first, an agent contains a relatively small system prompt describing its role, tone, business rules, and guardrails. As the organization grows, more instructions are added: Policies Compliance rules Business procedures Examples Edge cases Department-specific workflows Eventually the prompt becomes thousands of tokens long. Every user request forces the model to process every instruction—even when ninety-five percent of them are completely irrelevant. This hidden processing overhead is called the Context Tax. Rather than making agents smarter, larger prompts increase latency, raise inference costs, introduce reasoning noise, and gradually reduce answer quality. The presentation argues that the real problem isn't insufficient AI capability—it is forcing the model to continuously reason over information it doesn't actually need. WHY AGENTS DEGRADE OVER TIME Agent degradation is remarkably predictable. Organizations usually begin with one comprehens…","meta_description":"Many AI agents start out fast, responsive, and surprisingly intelligent. But after a few months of real-world use, something changes. Response times incre…","key_points":[],"chapters":[],"topics":[],"duration_seconds":4410,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/episodes/the-end-of-ai-bloat-why-modern-agents-need-skills/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365-7311214/the-end-of-ai-bloat-why-modern-agents-need-skills.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}