Coding agents from first principles
Build The Loop_
A minimal, practical blog about building a coding agent from scratch: the message loop, tools, permissions, memory, evals, and the engineering that makes the magic look ordinary.
Post 01
The Smallest Coding Agent Loop
At the center of every coding agent is a tiny primitive: send messages, run requested tools, feed the result back, and repeat until the model stops.
Series
12 parts
01
The Smallest Coding Agent Loop
Live
02Tools Are The Model's HandsDraft
03The Tool Calling LoopDraft
04A Safe WorkspaceDraft
05PermissionsDraft
06Building a CLIDraft
07Project AwarenessDraft
08MemoryDraft
09Context ManagementDraft
10Testing an Agent Without a ModelDraft
11Packaging ItDraft
12What Production Agents AddDraft