Context

Context

Also called: prompt context

Context is all the text a model can see for a single request: the system prompt, your message, the conversation so far, and any files or tool output the agent has pulled in. It is the only thing the model knows about your specific situation.

James Phoenix
Understanding Data Updated July 2, 2026

Because a model learns nothing from your conversation, context is everything. It is the complete bundle of text handed to the model on a given request, and it is the model's entire view of your task. If a fact is not in the context, the model does not know it, no matter how obvious it seems to you.

What goes into it

For a coding agent, the context on any request is typically assembled from:

  • The system prompt and the tool definitions.
  • Your instructions and any project rules the agent loads.
  • The back-and-forth of the current conversation.
  • File contents, command output, and search results the agent has gathered.

All of that competes for the same fixed space, the context window, and it is all measured in tokens.

Context is the lever you pull

Almost everything you do to get better results from an agent is a form of context management. Pointing it at the right files, clearing out finished work, stating a constraint plainly, giving it an example: these are all ways of shaping what the model sees. When an agent gets something wrong, the first question is rarely "is the model bad" and almost always "did it have the right context."

Tip
A good habit: before blaming the model for a wrong answer, ask what was actually in its context. Nine times out of ten the missing piece was information the model never had, not intelligence it lacked.

Related terms

Building with AI agents?

This dictionary is part of how I think about agentic engineering. If you want the same thinking applied to your codebase, that is what I do.

See how I can help