Maintaining project context and state for design decisions

Figma just shipped something worth a look.
You can now run your Figma Weave tools straight from ChatGPT, Claude, or Cursor through the Figma MCP server.

Say you built a brand mockup tool that turns product photos into mockups. Instead of opening Figma, you tell your agent: "run my brand mockup tool with these images." It finds the tool, runs it, tracks the progress, and drops the result back into your conversation.

The part I like is that your context stays with you. Prompts, images, brand guidelines, all of it. No tab hopping, no copy pasting things back and forth.

Figma says building new Weave workflows from inside your agent is next.
Design tools are quietly becoming things agents can call. That shift is bigger than any single feature here.

https://lnkd.in/gsWqNRY8

#Figma #MCP #AIAgents #DesignTools #AI

The first version of my design workflow was one enormous prompt. Thousands of words describing every step of how we design. I was pretty proud of it. It held together for about three steps and then quietly fell apart.

Not with an error. It failed the way a big prompt always does. The model lost the thread halfway down, blended two steps into one, skipped the one in the middle, and handed me something that looked like process but wasn't. And I couldn't fix it, because touching one part broke three others. One block of text, no seams.

The deeper problem was worse than maintenance. A single prompt gave the AI nowhere to stop. It ran from requirements straight to a prototype in one breath, sailing past every point where a human should have said "wait." It was automating the exact thing I'd promised to keep human.

Think of it as a team, not a prompt

The fix was to stop treating it as a prompt and start treating it as a team. A team isn't one person holding the whole job in their head. It's small roles with clear handoffs, and a check before the next person picks it up.

A design workflow where AI holds the context, I do the thinking: from brainstorm to prototype

The design process hasn’t changed. How much energy you have left for it has.

Let me say something that might surprise you.

After years of designing at scale — AI-powered tools for 1.6M Walmart associates, global experiences at Adobe, multi-product workflows at Intuit — I don’t think AI has fundamentally changed what good design requires.

You still need to talk to real users. You still need to understand the business. You still need to make judgment calls that no algorithm can make for you.

What AI has changed is everything around the design. The retrieval. The synthesis. The prep work. The 11pm Slack thread archaeology.

And that changes everything about how much of yourself you have left when you sit down to actually create.

...