Glossary

What is context engineering?

Context engineering is the practice of deciding what information a model sees at inference time — which documents, memories, tools, and instructions to place in the context window — so it produces accurate, grounded output. It has largely superseded "prompt engineering" as models and context windows have grown.

In depth

Understanding context engineering

Prompt engineering asked "how do I phrase the request?" Context engineering asks the bigger question: "what should the model have in front of it when it answers?" As context windows grew from a few thousand tokens to a million, the wording of the prompt matters less than the selection and structure of everything around it.

Good context engineering retrieves the right facts (not all facts), orders them well, includes the relevant tools, and leaves out noise that would dilute attention. Get it right and a general model behaves like a specialist; get it wrong and even a strong model hallucinates.

For a company, the raw material of context is institutional knowledge — brand, docs, policies, product data — which is exactly what a company brain organizes and feeds to agents.

See it in Clearly

Company Brain

Turn your org’s knowledge into context every agent can use.

The design workspace where these ideas are real

Agents that generate, a canvas they can see and drive, and a brain that keeps every asset on-brand. Free to start.