Introducing CAFE(S): A framework for defining AI context quality

Brian Houck of the developer-research firm DX defines five qualities of the instructions AI agents read, and argues that each shared instruction file needs a team that owns it.

AI agents act on the context they are given: the instructions, specifications and documents they read before they work. Brian Houck, a Distinguished Scientist at the developer-productivity research firm DX, wrote on Atlassian's blog about what makes that context good. He and four co-authors of a paper in the journal ACM Queue define five qualities: clarity, actionability, fidelity (being true and current), efficiency and security.

• Poor context once cost a developer a question to a colleague. It can now cost money, legal liability and security, as when Air Canada was held liable for a promise its chatbot made.
• Shared context files that many agents read should be reviewed like code, with more review the more widely a file is reused.
• Important context should have an owner and a review schedule, and the owner should be a team: "Ownership should follow teams rather than individuals, so context survives reorgs."
• Untrusted input should be kept apart from instructions. The authors cite a crafted email that made Microsoft 365 Copilot, Microsoft's AI assistant, leak internal documents.

A product team whose agents read shared design or product files can assign each file to a team and review changes to it like code. The authors write about engineering context, and the application to design and product files is an inference and is not their claim.

Derived by Working Surface from the article. Source line: Ownership should follow teams rather than individuals, so context survives reorgs.

28 September 2026: when agents build, people keep the first screen, the review, the files agents read and the whole product.