
Sign up to save your podcasts
Or


Welcome to Episode 429 of the Microsoft Cloud IT Pro Podcast. In this episode, Scott and Ben dig into the concept of LLM wikis, specifically building personal knowledge management vaults using Obsidian, markdown, and AI tooling like Claude Code, GitHub Copilot CLI, and Copilot Cowork. The core idea comes from a gist by Andrej Karpathy and involves creating a structured folder of markdown clippings that an LLM can reason over to extract entities, concepts, and sources, building a searchable, graph-linked knowledge base over time. Scott walks through how he wired up Obsidian Web Clipper and an RSS Dashboard plugin to feed articles into his vault automatically, then had the LLM help build a Python script to automate the ingest workflow and cut down on token usage.
The conversation expands into how Copilot Cowork fits into this workflow as a scheduling harness, with practical examples of using it to pull email from an inbox daily, convert messages to markdown, and generate a prioritized to-do list. Ben shares how he applied the same approach to 428 episodes of podcast transcripts, and both hosts note that token costs can run high fast without some upfront thinking about optimization. Scott closes with a reminder that pulling data into plain markdown sidecars outside of IRM and sensitivity label protections means teams should stay mindful of organizational data policies.
Your support makes this show possible! Please consider becoming a premium member for access to live shows and more. Check out our membership options.
Show Notes
Sponsors
The post Episode 429: Getting started with LLM Wikis appeared first on Microsoft Cloud IT Pro Podcast.
By Ben Stegink, Scott HoagWelcome to Episode 429 of the Microsoft Cloud IT Pro Podcast. In this episode, Scott and Ben dig into the concept of LLM wikis, specifically building personal knowledge management vaults using Obsidian, markdown, and AI tooling like Claude Code, GitHub Copilot CLI, and Copilot Cowork. The core idea comes from a gist by Andrej Karpathy and involves creating a structured folder of markdown clippings that an LLM can reason over to extract entities, concepts, and sources, building a searchable, graph-linked knowledge base over time. Scott walks through how he wired up Obsidian Web Clipper and an RSS Dashboard plugin to feed articles into his vault automatically, then had the LLM help build a Python script to automate the ingest workflow and cut down on token usage.
The conversation expands into how Copilot Cowork fits into this workflow as a scheduling harness, with practical examples of using it to pull email from an inbox daily, convert messages to markdown, and generate a prioritized to-do list. Ben shares how he applied the same approach to 428 episodes of podcast transcripts, and both hosts note that token costs can run high fast without some upfront thinking about optimization. Scott closes with a reminder that pulling data into plain markdown sidecars outside of IRM and sensitivity label protections means teams should stay mindful of organizational data policies.
Your support makes this show possible! Please consider becoming a premium member for access to live shows and more. Check out our membership options.
Show Notes
Sponsors
The post Episode 429: Getting started with LLM Wikis appeared first on Microsoft Cloud IT Pro Podcast.