Skip to content
Video
28:40

What actually makes a coding agent reliable

Evals, sandboxing and the unglamorous engineering that separates a demo from something you would let near a production repo.

agents
evals
reliability

Related

Building an agentic coding loop from scratch

A from-first-principles walkthrough of the read-plan-edit-verify loop that sits under every coding agent, built live with no framework.

Model Context Protocol in 20 minutes

What MCP is, what problem it solves, and how to write a server that a coding agent can actually use.