Turning Scattered Design Feedback into Tasks and Instant UI Reviews
An AI pipeline and review agents for a design copilot in Figma and FigJam
About the customer
Design reviews slow down when feedback is spread across many tools. Our client, a US company, builds an AI copilot for design work in Figma and FigJam. It turns comments, notes, documents, messages and video calls into actionable tasks, and gives feedback on UI designs using AI models trained on best-practice frameworks such as NNG, IDEO and Refactoring UI.
What needed solving
Scattered feedback
Design feedback was scattered across Slack, Google Notes, Figma comments and Zoom or Loom transcripts
Turning feedback into tasks
The scattered feedback had to be consolidated into actionable tasks
Consistent best practice
Designers also needed immediate, constructive UI feedback based on established best practices, for consistency and efficiency
How we built it
Data collection
Automated the collection of unstructured feedback from Slack threads, Google Notes, Figma file comments and meeting transcripts.
Task creation
Used LLM prompts tailored to each source to create relevant design feedback tasks in Linear, a project-management tool.
Platform integration
Passed the finished pipeline to the client’s production team to integrate into its platform.
Design review agents
Built AI agents trained on NNG, IDEO and Refactoring UI that give feedback on designs in Figma.
From unstructured feedback to a clear review process
Technologies
Domains
Have a Query? Let's Have a Conversation
Do you have a project in mind? We’d love to know what it is. Email us or send a message from our contact page.
Have a similar problem?
Tell us what you are trying to solve and our team will get back to you.