Unlocking creativity with GitHub and Figma
summary
GitHub demos a concrete design-to-code pipeline: GitHub Spark generates working prototypes (it runs the prompt three times to produce three variants and builds an LLM-backed to‑do app with a live “generate subtasks” button), GitHub Models lets designers compare side-by-side GPT‑4 vs 03 outputs and edit prompts, Copilot Agent Mode edits the real codebase and fixes lint errors, Copilot drafts and creates multiple issues from notes, and pasting a Figma URL into Copilot produces editable code tied to design system components.
AI-written summary · about
chapters (8)
- 0:00Design and code collaboration
- 4:57GitHub Spark for AI prototyping
- 10:58Evaluating AI models
- 14:07Prototyping features with Copilot
- 15:56Automating issues with Copilot
- 16:59Design to code with Figma
- 19:29Recap and future
- 21:15Q&A
related talks
20mAI will upend your process—for the better
40mUnlocking Productivity with GitHub Copilot Best Practices and Tips
22mCrafting design context for agentic coding workflows
47mUnlocking Productivity with GITHUB Copilot in 45 Minutes
01h 20mGithub Copilot - The World's Most Widely Adopted AI Developer Tool
49mUnlocking Success: Navigating the Code of Life with GitHub CoPilot
01h 05mThe Next Generation of Developer Productivity with GitHub Copilot & Visual Studio
01h 00mTips & Tricks: Get the Most Out of GitHub CoPilot