Context

Context is the relevant information the agent has access to right now. It is the abstract noun, not the raw input the model sees, which is the context window, and not the running history, which is the session. It means what the agent knows that is pertinent to the task. Loading something into context means making it part of that set, and context engineering is the discipline of curating it.

The three terms separate cleanly: context is the task-relevant information the agent currently has, the context window is the literal token sequence the model sees per request, and the session is the running conversation the harness stores.

The separation matters because context is a measure of quality, not quantity. A context window can be nearly full and the context still poor: thousands of tokens of stale tool output, none of it about the task at hand. It can also be nearly empty and the context excellent: the one type definition the task turns on.

Most day-to-day failures trace back to context. When the agent invents an API, contradicts a decision, or guesses at a schema, the first question is what was in context when it did. Usually the relevant fact was never loaded, or was buried under attention degradation. The fix is curation: load what the task needs, keep out what it does not.