A color block

The typical approach to agent context is either stuffing everything into the prompt or using vector search. Prompt stuffing hits token limits. Vector search works for semantic similarity but returns imprecise results when you need a specific value from structured data. Filesystems offer a different tradeoff: structure your data as files, give the agent bash, and the model brings the same capabilities it uses for code navigation.

Why filesystems work

Build a filesystem agent that uses bash tools and Vercel Sandbox to explore call transcripts and answer questions.

LLMs have been trained on massive amounts of code. They've spent countless hours navigating directories, grepping through files, and managing state across complex codebases. Agents have put in the time, and they already understand filesystems.

Cameron Youngblood

Building Filesystem Agents

In this course, you'll build a filesystem agent for analyzing call transcripts. The same pattern works for legal documents, coding agents, financial analysis, or SQL generation and execution.

Malte Ubl