Microsoft's recommended way to connect AI assistants like Claude Desktop to Dataverse used a local STDIO proxy, which was simple and suited individual developers. · THE DEATH OF THE PROXY
Enterprises now connect hundreds or thousands of agents across clients such as Claude Desktop, Claude Code, GitHub Copilot, Copilot CLI and custom orchestration services. · THE DEATH OF THE PROXY
Skills are becoming a foundation across Microsoft Copilot Studio, GitHub Copilot, Claude Code and the wider enterprise AI ecosystem. · The End of AI Bloat
Small Language Models (SLMs) are emerging as one of the most important developments in enterprise AI. While Large Language Models (LLMs) power tools like Microsoft Copilot with impressive reasoning and language capabilities, they also introduce challenges…
Custom integrations have long been one of the biggest bottlenecks in enterprise applications, but Dataverse MCP is changing that. In this episode of the M365.fm podcast, Mirko Peters is joined by Microsoft MVP Nathan Rose to explore how the Model Context…
Still wiring a local proxy to connect AI tools to Dataverse? This episode shows Power Platform architects and developers why the remote Dataverse MCP endpoint, secured with PKCE and Entra ID, turns Dataverse into a governed, multi-LLM backbone for Claude…
AI 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…
This episode of the M365.FM Podcast — “The Architecture of Persistent Context: Why Episodic AI Is Slowing You Down” — explains that persistent context is not a convenience feature but a foundational architectural layer that determines whether AI systems can…
Timeline of episodes about Claude
Articles about Claude (2)
Demystifying the Model Context Protocol (MCP) · Mirko Peters Welcome back, tech enthusiasts and podcast listeners! If you have been keeping up with our latest audio episodes, you know we have been diving deep into the rapidly…
Early MCP clients like Claude Desktop ran locally and needed a way to communicate with cloud services without an internet-facing endpoint. A local process translated between the AI client and Dataverse. · From the episode: THE DEATH OF THE PROXY
Which platforms use Skills?
The episode names Microsoft Copilot Studio, GitHub Copilot and Claude Code, along with the broader enterprise AI ecosystem. · From the episode: The End of AI Bloat
How is persistent context implemented?
The show notes describe a memory architecture with components like knowledge graphs and vector databases, and strategies like separating short-term and long-term memory using tools such as LangChain and Claude. · From the episode: Persistent Context Architecture for Copilot…
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Experts and companies for this topic
Nobody has listed this topic yet. Add it to your profile.