Interesting take. With agents, MCP and the right setup teams can address the "throw it over the wall" design to engineering hand-offs that plagued product development for decades. A design tool via MCP feeds into the dev env and with agent skills and plugins what's current in code can flow back to update the design. I've experienced these problems first hand at Amazon / AWS and as a side project I'm working on a human and agent friendly design system for building AI apps.
God I wish this guy wasn't completely wrong (and no offense to him, he just seems like a non-techie who doesn't understand LLMs yet) ... but he is wrong. Very wrong.
>Design teams have spent years trying to get people to actually read their design system documentation. Agents read it every single time.
They might read it, but that doesn't mean they listen to it. Every major LLM suffers from "context rot": the more you talk to it (and the more it does) the more context it uses up.
The more context it uses up, the less likely it is to listen to any individual instruction. That AGENTS.md file might get Claude to add the right button for the first half of your conversation with it, but I guarantee the longer the session goes on the more of that file it's going to ignore ... and that happens even faster if the user has tons of rules, memories, AGENTS.md files of their own, etc.!
The simple truth is that if you want this to really work with a diverse team where anyone can contribute, you need the same thing you always did: build tools (compilers, linters, etc.). In this case, you need a Claude who (with a fresh context) evaluates any MR to ensure it adheres to the design rules ... and even that Claude is not going to have 100% success.
Interesting take. With agents, MCP and the right setup teams can address the "throw it over the wall" design to engineering hand-offs that plagued product development for decades. A design tool via MCP feeds into the dev env and with agent skills and plugins what's current in code can flow back to update the design. I've experienced these problems first hand at Amazon / AWS and as a side project I'm working on a human and agent friendly design system for building AI apps.
God I wish this guy wasn't completely wrong (and no offense to him, he just seems like a non-techie who doesn't understand LLMs yet) ... but he is wrong. Very wrong.
>Design teams have spent years trying to get people to actually read their design system documentation. Agents read it every single time.
They might read it, but that doesn't mean they listen to it. Every major LLM suffers from "context rot": the more you talk to it (and the more it does) the more context it uses up.
The more context it uses up, the less likely it is to listen to any individual instruction. That AGENTS.md file might get Claude to add the right button for the first half of your conversation with it, but I guarantee the longer the session goes on the more of that file it's going to ignore ... and that happens even faster if the user has tons of rules, memories, AGENTS.md files of their own, etc.!
The simple truth is that if you want this to really work with a diverse team where anyone can contribute, you need the same thing you always did: build tools (compilers, linters, etc.). In this case, you need a Claude who (with a fresh context) evaluates any MR to ensure it adheres to the design rules ... and even that Claude is not going to have 100% success.