We are so excited about what this first ship lets us do next. You can read the full vector editing road map here:
https://t.co/ET9lhuapJm
We're working on fun new features like radial and line repeaters
Designed and built GEEIQ's @framer site from the ground up โ complete with custom animations showcasing the virtual worlds they cover.
Great to work with @CarlosGeeronimo on this one!
See video ๐
Hugely Grateful to have come 1st place ๐ฅin the @contra hosted @paper Challenge.
Excited for the future of the tool and what it can do.
Apologies for my audio!
Weโre LIVE with the @paper team announcing the winners of the Paper challenge.
Join to see who will take home $10K in prizes ๐ธ
https://t.co/2emCB00Unt
Today, weโre open-sourcing the draft specification for DESIGN.md, so it can be used across any tool or platform. Weโre also adding new capabilities.
DESIGN.md lets you easily export and import your design rules from project to project. Instead of guessing intent, agents know exactly what a color is for and can even validate their choices against WCAG accessibility rules.
Watch David East break down this shared visual language in action๐. New capabilities and links in ๐งต
My ideal AI design tool probably something like:
A canvas tool, where you can get any view of your app rendered to edit or use as the starting point for a new view. You can freely explore, duplicate, and make changes visually.
You could start these renders from other tools like @linear. User feedback -> render the screen to be edited.
It would have design language, system and product guidance files that help guide the overall design based on your product.
Each artboard carries metadata, like the origin of the view, who created it, what changes was made when, so you could query things across your whole team.
You could create areas that you want AI to fill or complete. Fill this list, complete the columns with this data or using this screenshot or something.
Edits in the artboard are tracked as a diff. You export those diffs as a plan for a coding agent to build against your actual codebase.
The design tool agents keep check-ins with the coding agent and try to communicate the nuances of the design so it gets built as a prototype.