Concept
Coding agents
A coding agent is an LLM wrapped in a loop that can read files, run commands, inspect outputs, and edit code until a goal is met. Think of it like an autocomplete assistant, except it acts on the environment instead of just suggesting text: it proposes a shell command or a…
The rest of “Coding agents” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→