All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Building a Personal AI Agent with Markdown-Based Skills and Local Models

By

Tomasz Tunguz

2d ago· 3 min readenInsight

Summary

The article describes a personal AI agent built on Pi that manages the author's inbox, calendar, deal pipeline, blog publishing, and research. The system uses two layers: a local markdown knowledge base (QMD) with ~80 workflow files for procedural guidance, and atomic SKILL.md files that each describe a single job. The approach allows frontier models to teach smaller, local models to perform real work without retraining, functioning more like a small operating system than a chatbot.

Key quotes

· 5 pulled
I've been using state-of-the-art models to teach small models running on my computer how I work.
My personal agent, based on Pi, runs my inbox, my deal pipeline, my blog publishing, my calendar, & my research.
It looks less like a chatbot & more like a small operating system.
The first layer is QMD, a local markdown knowledge base of about eighty workflow files in ~/memories.
The second layer is Skills, atomic SKILL.md files that describe one job each.
Snippet from the RSS feed
How a personal AI agent built on markdown skills lets a frontier model teach smaller, local models to do real work, without retraining.

You might also wanna read