@mattpocockuk: Thinking about a workflow like this for helping prevent comprehension debt on a fast-moving repo: Fast-moving repo w/lo…
Summary
Matt Pocock shares an idea for a workflow using LLMs to generate podcast summaries of code diffs, aiming to prevent comprehension debt in fast-moving repos; he has implemented it for his personal wiki with good results.
View Cached Full Text
Cached at: 07/12/26, 12:57 PM
Thinking about a workflow like this for helping prevent comprehension debt on a fast-moving repo:
Fast-moving repo w/lots of changes -> once per day/week, grab a diff of the changes -> feed it to an LLM to output a podcast transcript, focusing on the ‘why’ of what changed more than the ’what -> feed the podcast transcript to a TTS API -> publish to a private podcast feed -> listen on your commute/morning run/lunch break
I’m doing this for my personal wiki, which ingests from X/Slack/Discord/Gmail, and it’s super-efficient for keeping me in the loop.
Similar Articles
I built a version of Karpathy's LLM Wiki specifically for code repositories
A developer built a version of Karpathy's LLM Wiki adapted for code repositories, allowing users to store and retrieve insights from local code with automatic change detection.
@mattpocockuk: For folks following my personal wiki journey, it's going extremely well. Every weekday I have a 15-minute podcast on th…
Matt Pocock describes his personal wiki journey, using AI to generate daily podcasts from multiple data sources and build on-demand deep dives, along with a custom CLI for agents to help create course material, highlighting the power of owning your data.
@mattpocockuk: Prompt of the day: /retro read my last 10 coding agent sessions and find ways to make my repo easier to navigate. Find …
Matt Pocock shares a 'prompt of the day' that uses a retrospective review of recent coding agent sessions to spot where agents struggle to find information or rely on stale docs, arguing that improving repo navigability is an underrated way to save tokens.
@LufzzLiz: https://x.com/LufzzLiz/status/2058542686551028006
This article details the paradigm of incrementally maintaining a persistent markdown wiki using LLM (LLM Wiki), and open-sources the Claude Code skill along with multiple examples, including x-algorithm-wiki, to help developers automatically build a trusted architecture wiki for their project source code.
@tom_doerr: Self-correcting memory and context engineering for Claude Code https://github.com/rohitg00/pro-workflow…
Pro Workflow is a plugin for Claude Code and Cursor that adds self-correcting memory and persistent wikis using SQLite, allowing the AI to learn from corrections and build knowledge across sessions.