Use Case Intelligence RSS Search use cases Search
Anthropic Software / SaaS North America

Figma

Application Refactoring

Figma wanted teams to turn ideas and static designs into interactive software much faster, reduce the friction between design and development, and let non-coders prototype without rebuilding designs by hand.

Read the original story Explore all use cases
I prototyped a new product flow with Figma Make in five minutes.
I spent 30 hours teaching myself React to build my website. With Claude, I refactored and improved all that code in a single day
Working prototypes in minutes

Reported impact

Business outcome

Figma now lets designers, developers, and product managers create working prototypes in minutes, enables non-designers to visualize ideas, and shortens the path from mockup to functional software without waiting on a traditional design-to-development handoff.

  • Customer Experience
  • Productivity Improvement
  • Speed to Market

Solution

Figma integrated Claude into two creation paths: Figma Sites, where designers describe interaction changes against an existing web design, and Figma Make, where users start from a prompt or an existing Figma design and receive a working prototype or app. Claude generates the underlying code while preserving design intent, animations, responsive behavior, and pixel-level details instead of asking teams to recreate layouts from scratch. Figma continuously evaluates new Claude models and exposes the latest releases through an experimental-models setting, using Claude Sonnet as the model that first made the product viable and Claude Opus 4.6 for more complex, interactive builds. The round-trip between Figma Design and Make lets teams copy designs in, generate code-backed software, then return the result to the canvas for side-by-side iteration.

Data flow

A user starts from a prompt or existing Figma design, Claude inside Figma Sites or Figma Make generates the code and interactivity, and the resulting prototype or app can be brought back into Figma Design for further iteration and side-by-side comparison.

Solution architecture

5 components · 2 layers
  1. Compute
    • Claude Sonnet Delivered the code quality and speed that made Figma Make viable for production use.
    • Claude Opus 4.6 Generates more complex, highly interactive prototypes and apps in Figma Make.
  2. Serving
    • Claude Platform Provides the AI foundation Figma uses to translate designs and prompts into interactive software.
    • Figma Sites Lets designers add interactivity to existing website designs using natural-language prompts.
    • Figma Make Turns prompts or existing Figma designs into code-backed prototypes and apps.

Architecture clues

  • Claude is used both for prompt-first generation and for adding interactivity to existing designs.
  • Figma exposes new Claude releases through an experimental-models setting inside Figma Make.
  • The workflow supports round-tripping between Figma Design and Make.

Evidence from the source

Claude Sonnet consistently delivered on code quality, design intent, and speed
Claude transforms them into fully functional prototypes with complex logic, animations, and responsive behaviors.
Figma Make is a way to go from idea to real software.
I prototyped a new product flow with Figma Make in five minutes.
The first allows designers working in Figma Sites to add interactivity to existing website designs by describing what they want
Transparency Evidence & methodology 90/100 reference value · 79% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Anthropic

    Figma customer story

    First-party
    https://claude.com/customers/figma
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Feb 6, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Anthropic Archived · Mar 10, 2026 Stripe Software / SaaS North America Stripe needed a CLI-native coding assistant that met enterprise security requirements and could be safely distributed to engineers without exposing corporate laptops to unapproved JavaScript packages or an unmanaged npm… 1,370 engineers using Claude Code Application Refactoring Claude Code · Claude models OpenAI Oct 9, 2026 Asana Software / SaaS North America Asana needed to cut the cost and latency of its StackAI browser agent so it could offer customers more capable models for browser-driven workflows without unsustainable operating expense. $0.47 average estimated model cost with the optimized GPT-6.1 Sol workflow Application RefactoringIT Operations Automation Codex · Command · GPT-6 Astra OpenAI Oct 8, 2026 Braintrust Software / SaaS North America Braintrust wanted to respond to customer feature requests faster and run more engineering experiments, but slower coding tools and backlog-driven workflows made it costly to turn feedback into working prototypes in real… 50% of the Braintrust team moved to Codex in one month Application RefactoringIT Operations Automation Codex · GPT-5.5