Glossary / Prompting & Context

Context

The information the AI can see right now while it works.

Updated July 2, 2026

Context isn’t vibes, and it isn’t memory in the human sense. It’s the working material on the desk right now.

Use the desk frame: the papers in front of you change what you can do. The contract, notes, and checklist on the desk let you work; the same files locked in a cabinet down the hall don’t help. The desk can also get too crowded, which is where the context window matters: pile every company document in front of you and the important page disappears. Good context isn’t maximum context. It’s the right context for the job.

How it shows up

In a Claude project, project knowledge is context you attach on purpose. In a WorkDesk or vault, it’s notes, transcripts, rules, and prior decisions. In RAG, the system retrieves relevant chunks from a knowledge base and brings them onto the desk. This is why context management is the reason the whole thing works: organize the right files and an agent picks up the work fast; leave them scattered and it guesses or burns time searching. Context also has shape: stable context is durable (who the client is, what rules apply), current context is this session (the latest request, the file being edited).

Why you care

Better context usually beats a cleverer prompt. Give the AI the wrong papers and it produces the wrong work with confidence. Give it the right ones and the work gets sharper, faster, and easier to review. AI doesn’t need you to sound technical. It needs you to make the work visible.