The CAFE(S) framework: Improving AI agent effectiveness

A four-person team including Max Kanat-Alexander of Capital One, Eirini Kalliamvakou of DX, and Margaret-Anne Storey of the University of Victoria introduced the CAFE(S) framework on the Engineering Enablement podcast, defining five properties of high-quality AI agent context: Clarity, Actionability, Fidelity, Efficiency, and Security. The co-authors argue that improving models and harnesses is not enough to maximize agent effectiveness, and that poor context — ambiguous instructions, irrelevant information, insecure access — drives runaway token usage, incorrect outputs, security breaches, and developer toil. They cite a real-world case in which an agent found an unrelated API credential and deleted a production database, and contend context review could become as important as code review because a mistake in a widely used instructions file repeats in every session.

Listen and watch now on YouTube https://youtu.be/V32mImG3Lg8 , Apple https://podcasts.apple.com/us/podcast/engineering-enablement-by-abi-noda/id1619140476 , and Spotify https://open.spotify.com/show/3NxjyIsuxeDMQtisDqBy7D . As AI agents become more capable, context quality is increasingly the limiting factor in their performance. In this episode of Engineering Enablement , I’m joined by my CAFE S co-authors Max Kanat-Alexander Capital One , Eirini Kalliamvakou DX , and Margaret-Anne Storey University of Victoria to introduce our framework for evaluating whether agents have the context they need to do their jobs well. We introduce the five dimensions of CAFE S : Clarity, Actionability, Fidelity, Efficiency, and Security. We walk through common context failures, how poor context accrues technical and cognitive debt, what it costs in developer productivity and operating spend, how AI is changing the skills engineers need, and why context review could become as important as code review. Some takeaways: Why context quality matters for AI agents - Improving models and harnesses isn’t enough to maximize AI agent effectiveness. The quality of the context agents receive is just as important, yet organizations rarely evaluate it systematically. - Poor context creates compounding costs and risks. Ambiguous instructions, irrelevant information, and insecure context can lead to runaway token usage, incorrect outputs, security breaches, and additional developer toil. The five dimensions of the CAFE S framework - CAFE S defines five properties of high-quality context: clarity, actionability, fidelity, efficiency, and security. Each addresses a distinct failure mode and helps identify where context needs improvement. - Clarity may be the most important dimension because ambiguity is often invisible to the person providing instructions. Agents can’t reliably infer unstated assumptions, and an incorrect interpretation can compound throughout a task. Why model failures are often context failures - Agents frequently make mistakes because critical knowledge exists only in developers’ heads. Without documented requirements, constraints, and decisions, agents may build unwanted features or take actions that conflict with the team’s intent. - Security failures can stem from giving agents access to information they shouldn’t have. One real-world example involved an agent finding an unrelated API credential and deleting a production database. How poor context contributes to technical, cognitive, and intent debt - Undocumented goals, constraints, and decisions create intent debt that can become more costly with AI agents. Agents need access to the reasoning behind decisions, including what a system should not do. - Better context can help prevent debt, but successful agent workflows can also encourage complacency. Teams may stop documenting important decisions when agents appear to be working well. Creating high-quality context is becoming a core engineering skill - AI fluency involves learning to anticipate what agents need rather than correcting mistakes after they happen. More experienced developers proactively define goals, constraints, and success criteria based on lessons from previous failures. - Skills traditionally associated with senior engineers may become essential at every level. Clearly communicating intent and requirements has long been part of senior engineering roles, but AI agents are making those skills increasingly important for all developers. Why context review could become as important as code review - Shared context deserves more scrutiny because its effects multiply across agent interactions. A mistake in a widely used instructions file can be repeated in every session, while an improvement can make every agent more effective. - Context review should be proportional to the importance and reach of the information. Critical shared instructions may need formal review, while lightweight documentation updates should remain easy to make. - Reviewing context can also build shared understanding across engineering teams. Like code review, the process can help developers align on requirements, decisions, and the intended behavior of their systems. In this episode, we cover: 00:00 https://www.youtube.com/watch?v=V32mImG3Lg8 Intro 01:18 https://www.youtube.com/watch?v=V32mImG3Lg8&t=78s Meet the CAFE S authors 03:13 https://www.youtube.com/watch?v=V32mImG3Lg8&t=193s Introducing CAFE S : Why context quality matters 06:32 https://www.youtube.com/watch?v=V32mImG3Lg8&t=392s Common context failure modes 08:30 https://www.youtube.com/watch?v=V32mImG3Lg8&t=510s The five dimensions of high-quality context 12:33 https://www.youtube.com/watch?v=V32mImG3Lg8&t=753s When model failures are actually context failures 18:24 https://www.youtube.com/watch?v=V32mImG3Lg8&t=1104s Why the panel prioritizes clarity in CAFE S 22:34 https://www.youtube.com/watch?v=V32mImG3Lg8&t=1354s How context quality relates to technical, cognitive, and intent debt 25:35 https://www.youtube.com/watch?v=V32mImG3Lg8&t=1535s How human interventions reveal context failures 28:11 https://www.youtube.com/watch?v=V32mImG3Lg8&t=1691s How context quality relates to AI fluency 30:28 https://www.youtube.com/watch?v=V32mImG3Lg8&t=1828s How AI is changing what makes a good engineer 33:48 https://www.youtube.com/watch?v=V32mImG3Lg8&t=2028s The case for context review as a discipline 38:44 https://www.youtube.com/watch?v=V32mImG3Lg8&t=2324s Wrap-up Where to find Margaret-Anne Storey: • LinkedIn: https://www.linkedin.com/in/margaret-anne-storey https://www.linkedin.com/in/margaret-anne-storey • X: https://x.com/margaretstorey https://x.com/margaretstorey • Website: https://margaretstorey.com https://margaretstorey.com Where to find Max Kanat-Alexander: • LinkedIn: https://www.linkedin.com/in/mkanat https://www.linkedin.com/in/mkanat • X: https://x.com/mkanat https://x.com/mkanat • Website: https://www.codesimplicity.com https://www.codesimplicity.com Where to find Eirini Kalliamvakou: • LinkedIn: https://www.linkedin.com/in/eirini-kalliamvakou-1016865 https://www.linkedin.com/in/eirini-kalliamvakou-1016865 Where to find Brian Houck: • LinkedIn: https://www.linkedin.com/in/brianhouck https://www.linkedin.com/in/brianhouck Referenced: • CAFE S : Your Agent Is Only as Good as Its Context https://getdx.com/whitepaper/the-cafes-framework/ • The Productivity-Experience Paradox - Annie Vella https://annievella.com/posts/the-productivity-experience-paradox/ • From Technical Debt to Cognitive and Intent Debt: Rethinking Software Health in the Age of AI https://arxiv.org/abs/2603.22106