“We are evolving Stitch into an AI-native software design canvas,” Rustin Banks, product manager at Google Labs, wrote on company’s blog, Keynote. “With it, anyone can create, iterate and collaborate to turn natural language into high-fidelity UI designs.”

Launched last March during the Google I/O annual developer conference, Stitch sets out to give people an accessible tool for creating front end UI designs for projects like websites or mobile apps. While late to a market already occupied by competitors like Figma and Cursor, Stitch’s new features are catching the industry’s attention and posing a threat to incumbent platforms that are scrambling to keep up with the relentless pace of AI design software updates.

What’s new in Stitch

The announcement outlined five major AI-powered updates to the platform including integrations with other AI platforms, voice capabilities, design agents. Among the major updates is a complete redesign of Stitch’s UI: an infinite canvas similar to Figma’s which allows for all project iterations to be in one space. The canvas also allows text, images, or code to be added to the canvas as context.

Google also introduced AI agents with a design agent tailored for design reasoning, as well as an agent manager to keep organized when working on multiple ideas at once.

Stitch expanded its existing design system toolkit, which allows users to import or export design rules and use, and can now be used with DESIGN.md, an agent-friendly markdown file.

“This lets you, for instance, apply your designs to a different Stitch project so you don’t have to reinvent the wheel every time you start,” writes Banks.