Launched this week
Design In The Browser
The visual tool for frontend. Point, click, and let AI code.
152 followers
The visual tool for frontend. Point, click, and let AI code.
152 followers
Design In The Browser lets you point at any element on your website and tell AI what to change. Click a button, a heading, or select text — describe your edit in plain language, and it sends the instruction (with a screenshot) directly to Claude Code, Cursor, or Gemini CLI running in the built-in terminal. No more copying selectors or describing layouts in chat. You see it, you change it, and AI does it. Supports multi-edit queuing, responsive viewports, and your preferred code editor.
Design In The Browser
Prototypr
@assentorp well done Peter, great it works with lcaude code
@assentorp Congrats on the launch! What’s the hardest frontend pattern for AI to generate cleanly?
SEMrush
Looks awesome! Does it work with more sophisticated requests like creating icons and illustrations? Can it learn from brand style guidelines / a design system?
Design In The Browser
Hi@alina_petrova3
It works best for things that live in the codebase.
Icons: Yes. If your icons are SVGs (inline files or icon components), you can ask it to generate new SVG icons or tweak existing ones (stroke, size, alignment, variants), depending on what Claude / Gemini / Cursor can produce.
Illustrations: Not really. It won’t create illustration assets, it’s not an image generator.
Brand guidelines / design system: It won’t “learn” your brand permanently, but if your tokens/components/guidelines are in the repo (or you paste a short rules snippet), the AI can follow them and apply them consistently.
CCgather
Oh..!
Congrats! 🎉
Less explaining = less tokens.
Love it.
Design In The Browser
@dhxyoon Thanks, glad you like it. If you have any feedback let me know.
Congrats on the launch! Love how Design In The Browser turns “I see it, I change it” into real AI-powered frontend edits—perfect bridge between live UI context and coding agents.
Interesting idea. Will there be integration with Canva or other design AIs? For now, general-purpose AIs don’t always generate high-quality design.
Design In The Browser
@mykyta_semenov_ No there will not be an integration with Canva. I get quite good results with the frontend design skill. Have you tried that?
@assentorp Minor frontend tweaks — I agree, AI handles those well. But when it comes to building entire design elements or even full pages, problems can arise specifically at the design stage. In other words, there’s a need for a tool that can both produce high-quality design itself and then generate the frontend based on that design. Right now there are many separate tools, and that makes the process complex.
This is just an idea on how you could evolve your service to better differentiate it from competitors.
Just watched the demonstration video and it is quite intuitive to use.
Congrats on the launch of it!
I'm guessing its main for HTML/CSS, right?
While watching the video, I was imagining myself using this over Figma, to get Flutter codes being output.
I already do this with Claude, sharing images and instructions to get some UIs quickly prototyped.
Would be nice having a tool like yours for making this process faster.
Do you have, or are you planning, a browser extension?
Would be awesome for getting references on the fly. Sometimes you see a reference that perfectly fits something you have in mind for a project, and being able to capture it ( in code ) would be beautiful.
Design In The Browser
@marcelo_bottoni No plan on browser extension, currently looking for feedback/ideas to improve it. It is mainly build for frontend work. So whatever change you normally would type to an agent to do, it can do. It just makes it easier instead of back and forth between the browser and the terminal.
You can already reference other stuff, for that you will take a screenshot and added to the prompt via the Image icon. It then takes that into context when you send the prompt.