Figma Launched an AI Assistant for Text-Based Design Creation

Figma launched an AI assistant within its collaborative canvas. The assistant generates new designs based on text requests, edits existing mockups, and creates multiple project variations with a single click. It works directly in the shared canvas where the team develops the design together. The AI is expected to save hours on routine tasks like iterations and testing variations. Trend: AI tools are becoming a standard part of designer workflow. The assistant understands the full context of a project — brand style, color palette, iconography, typography, and other brand guidelines already defined in the file. This means each variation created by AI will be aligned with the project's style and won't require additional revisions. Designers can now request multiple options without switching between tools.

AI-processed from TechCrunch; edited by Hamidun News
Figma Launched an AI Assistant for Text-Based Design Creation
Source: TechCrunch. Collage: Hamidun News.
Listen to article
Article Fact Sheet & Key Figures
ParameterDetails
Primary sourceTechCrunch ↗
Editor-in-Chief
Key metric #1Generating entire interface screens from scratch based on function descriptions
Key metric #2Creating 5-10 variations of a button, heading, icon, banner, or background at once
Key metric #3Scaling design for different screen sizes (mobile, tablet, desktop, smart TV)

Figma added a built-in AI assistant to its collaborative canvas — a platform for collaborative design work.

What the Assistant Can Do

Figma's AI agent generates new designs based on text commands, edits existing mockups, and automates the creation of iterations. The assistant understands the context of the entire project: brand style, color palette, iconography, typography, and other brand book elements already in the file. This means that each variation created by AI will be aligned with the project's style and won't require additional work.

Example: you write "make a button in minimalist style, blue background, white text, add a 2px shadow." The AI will create multiple options to choose from — different button heights, different shades of blue, different corner radius values. If typography and corporate colors are already defined in the project, the assistant will automatically account for them.

Integration into the Workflow

The assistant is embedded directly in the collaborative canvas, where the entire team edits the design simultaneously. This is fundamentally different from the traditional workflow: previously, a designer would go to ChatGPT or Midjourney, write a prompt there, get a result, then copy it back to Figma and adapt it. Now everything is in one interface.

The AI's suggestions are immediately visible to all colleagues, and you can discuss options in the context of the project. The developer sees the ready specification. The product manager can immediately notice if the button looks different. There's no need to send files, write comments in Slack, or wait for responses. Text commands eliminate the need to open a separate AI tool — everything is in one place. Fewer tab switches, more focus on design.

Concrete Use Case Examples

The assistant can speed up work on:

  • Generating entire interface screens from scratch based on function descriptions
  • Creating 5-10 variations of a button, heading, icon, banner, or background at once
  • Scaling design for different screen sizes (mobile, tablet, desktop, smart TV)
  • Finding color options, palettes, and typography for experiments
  • Auto-filling mockups with realistic placeholders, text samples, and data
  • Reworking existing design in a new style or for a new brand book

What This Means for Designers and Teams

AI is moving from separate tools directly into working platforms. For designers, this means that routine tasks — finding options, adapting for different screens, adjusting to brand guidelines, iterating with clients — will happen many times faster. But this is not a replacement for humans.

The AI assistant takes on mechanical work, while the designer focuses on strategy, creativity, and solving complex problems. Instead of manually redoing a button 20 times in Figma, a designer asks AI to do it, selects the best option, and moves on. Time savings — hours per day.

Such tools change the speed of work, quality of life in the profession, and how companies work on products. AI tools are becoming not a luxury, but a basic part of the stack. The next generation of designers will work alongside AI as a matter of course.

Story

Key Questions Answered

What the Assistant Can Do?

Figma's AI agent generates new designs based on text commands, edits existing mockups, and automates the creation of iterations. The assistant understands the context of the entire project: brand style, color palette, iconography, typography, and other brand book elements already in the file. This means that each variation created by AI will be aligned with the project's style and won't require additional work. Example: you write "make a button in minimalist style, blue background, white text, add a 2px shadow." The AI will create multiple options to choose from — different

What are the key details on Integration into the Workflow?

The assistant is embedded directly in the collaborative canvas, where the entire team edits the design simultaneously. This is fundamentally different from the traditional workflow: previously, a designer would go to ChatGPT or Midjourney, write a prompt there, get a result, then copy it back to Figma and adapt it. Now everything is in one interface. The AI's suggestions are immediately visible to all colleagues, and you can discuss options in the context of the project. The developer sees the ready specification. The product manager can immediately notice if the button loo

What are the key details on Concrete Use Case Examples?

The assistant can speed up work on: Generating entire interface screens from scratch based on function descriptions Creating 5-10 variations of a button, heading, icon, banner, or background at once Scaling design for different screen sizes (mobile, tablet, desktop, smart TV) Finding color options, palettes, and typography for experiments Auto-filling mockups with realistic placeholders, text samples, and data Reworking existing design in a new style or for a new brand book

ZK
Zhemal Khamidun — CPO at Alpina Digital, product manager of AlpinaGPT. Building AI products since 2019. Hamidun News is a pet project that grew into a production aggregator with 6,000+ readers.
✦ Hands-On AI Engineering · Hamidun Academy

Build & Ship Production AI Agents Without Boilerplate Code

Start your free 72-hour trial at Hamidun Academy (academy.hamidun.com) — interactive lessons on Claude Code & Cursor, live Tech Radar, and production agent templates.

Start 72h Free Trial →Vibe-Coding Intensive
What do you think?
Loading comments…