# attenzione please > short, opinionated notes on ai and product. each note answers one question, and starts from a real conversation, anonymized. --- id: 3 title: "how do you get ai agents to actually use your design system?" description: "put it all in one place the agent can query: the component library with its metadata, examples and automated checks. not a giant agents.md plus a separate doc on how to use the components." date: 2026-11-17 updated: 2026-11-17 tags: [design-systems, agents, storybook] url: https://attenzioneplease.com/notes/how-to-get-ai-agents-to-use-your-design-system --- # how do you get ai agents to actually use your design system? put it all in one place the agent can query. the component library, with the metadata, examples and automated enforcement inside it. for us that's storybook. a giant agents.md plus a separate markdown on how to use the components doesn't hold up. ## what went wrong first on one project the agent said it was using the right data grid component. the designer looked at the result and said no, that's not it. the grid wasn't documented well in the storybook, which was probably the reason. a teammate's read was simple: the main problem is that the design system is incomplete. so before blaming the model, ask. is the design system amazing and the ai just got it wrong? what can be improved in the design system? does it have metadata? are the components properly described? ## one place, not three design.md is how components should look. storybook is which components the agent must use, with examples and automated enforcement. it doesn't make much logical sense to have a component library, which can embed the metadata, plus a markdown on how to use it. if it can all be done in one place, do it all in the storybook. scalable, reliable, without reinventing the wheel. and please no super long agents.md. that pollutes the context for every engineer working in the repo. ## it's not just mcp an mcp on top of the design system lets the agent query the component list, its metadata and the actual component code, so it doesn't have to guess how the components look. useful. but it's not just mcp. it's the metadata and the tests that come with it. the goal is to make the design system knowledge discoverable and testable for any agent. ## put the check in ci visual review runs in ci. when you approve the changes in chromatic, the ci check passes and then you can merge. no approval, no merge. ## how to know it works take the old setup and the new one. same prompt, compare results --- id: 2 title: "do you still need a ui/ux designer if ai can build the screens?" description: "for something new, yes. for a feature you can build from components you already have, mostly no. the design system is the job now." date: 2026-11-17 updated: 2026-11-17 tags: [design, design-systems, product, ai] url: https://attenzioneplease.com/notes/do-you-still-need-a-ui-ux-designer --- # do you still need a ui/ux designer if ai can build the screens? for something new, yes. for a feature you can build with components you already have, mostly no. if the design system is good, anyone can build the feature and what comes out is good. the designer's real job moves to the system. ## the roles are collapsing some roles are expanding and some others are being crushed. so the question is, why can't a product manager just get it done on their own? they don't need to go through figma anymore. the feeling i get is that ui/ux on its own is useless. you need a system. once you build on top of a top notch system, things kind of fall in place on their own. ## when you need a designer when you start from scratch. no design system, no clear identity. you need someone with judgment, on the graphic side and on ui/ux, to build it for you. and when you build something completely new. new components, new ways of showing the data. then yes, you need a new piece of the design system. ## when you don't you implement a new feature with three components you already have, they work really well together. why do i need you? maybe just to confirm, hey, do you like it? the review can be done by the product manager. one of our designers put it well. we're all builders now and we're all reviewers. we just review with the background we have. ## the pushback i got not everyone on the team agrees with me, which is good. one take: in a market saturated with ai products, design is what makes you different. without it you get a twin of something that already exists. component libraries let you move faster on the small features, so designers can spend their time on the big things that start from zero. another: the biggest value is strategy. defining the problem, what we focus on, and how it ties to the bigger context. and after execution, having the criteria to tell when a design is good or feels generic. i agree with both. it still points to the same place. ## the design system is the job a top notch design system means engineering of the design system. the front end components need to be thought out with an engineering mindset, then the design side. engineering and design together give you the foundations. after that everyone can contribute. and if ui generated on the fly becomes more and more common, like a ui an mcp returns for the exact query the user sent, the design system matters more. maintaining it matters more. enforcing it through the whole development process matters more. if you maintain the design system well, your goal should be to make yourself irrelevant --- id: 1 title: "what is an ai harness, and how is it different from the model and the app?" description: "think of a restaurant. the model is the chef, the harness is the kitchen, the app is the front of the house. you can use the inside without the outside, never the outside without the inside." date: 2026-11-17 updated: 2026-11-17 tags: [agents, harness, ai] url: https://attenzioneplease.com/notes/what-is-an-ai-harness --- # what is an ai harness, and how is it different from the model and the app? think of a restaurant. the model is the chef, the harness is the kitchen, and the app you type into is the front of the house. you can use the inner layers without the outer ones, but not the outer ones without the inner ones. ## the chef is the model the model is raw intelligence. talent. a chef who studied every cookbook and is incredibly good at cooking. but without the fire he doesn't cook. and without the recipes coming in, which is the context, he doesn't know what to make. a few years ago the chef was already there, there just wasn't a kitchen powerful enough. so he did his own small things. ## the kitchen is the harness model, tools, prompts and max steps. that's a harness. take the output of a model and pass it back to a model again, that's already a harness. it's a loop. when i say harness i include its configuration. the configured harness has the recipes. which tools the model gets offered is up to the harness. and a kitchen does nothing on its own if there's no place to go eat. ## the front of the house is the app you walk into the restaurant, sit down, the forks are there. you don't see any machines. that's chatgpt.com. take images. the chatgpt app doesn't make the image. the harness passes the request to the model, the image comes back, and the app shows it to you nicely. same as google. the google ui isn't google. there's a front end, a back end and a lot of stuff around it. claude code is partly a harness. it's an app plus anthropic's harness underneath. codex is the same with openai's. and one harness can sit behind several apps, a web app and a terminal app can both use the same one. ## then where is the agent? when you resume a session in the terminal you're resuming an agent. it's your harness with the mission you gave it, already in motion. same in chatgpt. you write "hi, send an email" and it starts doing things. that's an agent you created by invoking the harness through the interface, which then uses the model. ## and the waiter there's also a proxy. it's where the orders pass. the waiter takes your order to the place that handles orders, and if you ask for something bad he tells you no, we can't make that. but forget about it for now, it's not the point. ## why everyone mixes them up the harness is invisible. nobody sees it. if you never built something with a model in code, you don't get what it is. to most people chatgpt just does more stuff now. i didn't invent the kitchen thing btw. but it works really well, i think