Here are 5 major upgrades to help you create, iterate and collaborate:
🎨 AI-Native Canvas
🧠 Smarter Design Agent
🎙️ Voice
⚡️ Instant Prototypes
📐 Design Systems and DESIGN.md
Rolling out now. Details and product walkthrough video in 🧵
Here is a quick walkthrough of everything new in Stitch:
🎨 The AI-native canvas can hold and reason across images, code, and text simultaneously. The new agent manager helps you design in parallel. (PS … light mode!)
🧠 A smarter design agent now understands your entire canvas context. You can swap images, generate product briefs, or mix mobile and desktop screens on the same canvas.
🎙️ You can vibe design with your voice (in Preview). Stitch can ‘see’ your canvas and your selected screens. You can ask for design critiques, variations, or navigate your canvas.
⚡️ Instant prototypes. Just hit the play button to see a prototype or preview your app in seconds. Stitch can imagine the next screen based on your mouse click.
📐 DESIGN.md and consistency. Every new design automatically starts with a cohesive design system which vastly improves consistency. The new DESIGN.md file can be used to export or import your design rules.
Walkthrough video👇 Details for each major improvement 🧵
🎨AI-Native Canvas
We are introducing a complete redesign of the Stitch UI with a node-based infinite canvas:
✨ This spatial canvas accepts images, code, and PRDs as creative seeds
✨ The new Agent Manager helps you work on many ideas in parallel and keeps you organized
✨ Clicking a task in the agent manager takes you to the relevant screens
✨ Light mode! Sometimes some extra contrast can be helpful, especially when working on darker screens
🧠Smarter Design Agent
A completely new design agent understands your entire canvas context. Try asking it:
✨ “Swap out the logo (or profile image) with the one I just uploaded”
✨ “Make a product brief from these screens and put it on the canvas”
✨ “Interview me to help me design a new landing page for my brand”
✨ “Make a mobile version of these screens” (we heard you! you can now mix mobile and desktop screens on the same canvas!)
🎙️Voice (Preview)
We believe that your voice will be the future driver of design:
✨ In voice mode, Stitch can "see" what you are working on and what you click on (“change this screen”)
✨ Stitch acts as a sounding board to give you real-time design critiques
✨ Tell Stitch to make an update, then another one…. and another one, Stitch works on it all concurrently
✨ Ask it to navigate the canvas completely hands-free (“show me the dashboard screen”)
As a preview feature, expect rapid improvements in voice in the coming weeks
⚡️Instant Prototypes
Click 'Play' to instantly preview your interactive app flow.
✨ Stitch automatically assesses the order of screens and adds connections
✨ You can ask Stitch to automatically generate the logical next screen based on where you click
✨ Here you can design transitions, and interactions [coming soon]
✨ You can even see the "states" of different screens, like logged in versus logged out views
✨ Share a direct link to your prototype (or mobile QR code)
📐Design Systems and DESIGN.md
Consistency using Design Systems and DESIGN.md:
✨ Every new design automatically starts with a cohesive design system which GREATLY improves consistency (we heard you!)
✨ Edit the system, and all associated screens can be easily updated
✨ You can extract a design system from any URL
✨ Use DESIGN.md to export your design rules or import your design rules from other products (just ask your agent to create you a DESIGN.md file from your code or other context)
✨ You can start a new design by choosing from popular design systems
✨ Read more about DESIGN.md in the docs (link in thread)
Thanks for all of your feedback. We took it in, and built this for you... 🫶
We're also thrilled to announce our $4.4M seed round, led by @KhoslaVentures (@SVenkatachalam).
Our investors include design leaders such as @joulee, @davidhoang, @becker513,@anishaj, as well as company operators like @howietl, @mattjackrob, @jjeremycai, @joelhellermark alongside many other esteemed industry leaders and experts.
This funding will supercharge our AI research and keep us at the forefront of UI generation.
Building an AI for design was a massive challenge, as language models simply don’t understand the subtleties of interface design.
To solve this, we trained a language model with the latest AI techniques and industry-standard design principles to make it proficient in interface design.
After months of dedicated effort, this hard work has led to a significant breakthrough. We are excited to share this new model with you today!