How Figmates Used Figma AI to Take Delight to the Next Level | Figma Blog

Figma’s 2026 April Fun Day project, “FigCade,” used Figma Make, Figma Weave, and the Figma MCP server to create six playable mini-games in only a few days. The tools helped the team rapidly prototype ideas, explore visual styles, produce media, and translate designs into code. The project demonstrated how AI can make design and development more collaborative and iterative.

Building a playful canvas experience

• April Fun Day is Figma’s annual tradition of adding playful surprises and Easter eggs for its community.
• This year, the team brought six mini-games directly into the Figma canvas for one week.
• The project also gave employees an opportunity to experiment beyond their usual roles and push Figma’s tools in new ways.
• The resulting FigCade included games such as:
  • 2Fast2Figma, a timed quiz about Figma facts.
  • FigPalette and Diabolical Magic Square, featured in the game menu.

Rapid prototyping with Figma Make

• Figma Make helped the team turn ideas into working prototypes quickly.
• An early concept for 2Fast2Figma was created on a Sunday morning and became functional that afternoon.
• The team generated multiple prototypes, tested them with others, and iterated based on feedback.
• This established a fast workflow: build something quickly, review it, align with the team, and refine it.

Exploring visuals with Figma Weave

• Figma Weave helped designers generate and explore visual assets more efficiently.
• Designer Lesley Moon used it to create felt-style textures and assets, including the project’s textured cursor.
• Generating many variations quickly expanded the range of visual themes the team could consider.
• Weave was also used to develop the April Fun Day trailer:
  • Product Manager Tara Nadella explored the initial concept.
  • Motion Designer Fifi Law used those explorations and Lesley’s visuals to produce the final trailer in one day.

Connecting design and code with MCP

• The Figma MCP server helped developers turn design explorations into implementation.
• Engineer Steven Noto used Claude and GitHub Copilot with MCP authentication.
• By sharing links to specific Figma components, the coding agents could access design context and generate code matching the intended specifications.
• The team moved back and forth between design and development, using AI to reduce the distance between visual concepts and working software.

Practical takeaway

FigCade illustrates how combining rapid prototyping, generative visual tools, and design-aware coding assistance can help small teams create polished interactive experiences quickly. The strongest results came from treating AI as part of an iterative design-and-development process rather than as a replacement for human direction.