← back
Excalidraw: AI and Human Whiteboarding Partnership - Christopher Chedeau
Takeaway
Treat AI as a chance to rethink the product, not as a sprinkle on the old UI — and only ship AI features that match how users actually use your tool.
Summary
- Chedeau traces Excalidraw's origin (active-procrastination from a Facebook perf review) to becoming the de-facto online whiteboard during COVID by rejecting one-to-one mapping of physical whiteboard limits (fixed size, pixel erasing, hand-traced text).
- Draws an analogy: AI integrations today are 'sprinkling AI' on existing UX the same way early online whiteboards mimicked physical ones — a mistake.
- Excalidraw experiments: a Fal.ai model turning sketches to real beach photos was cool but users don't draw realistic images; LLMs generating raw Excalidraw diagrams initially failed; success came with intermediate 'mages' format and Gemini reportedly outputting Excalidraw files directly.
- Key lesson: just because a model exists doesn't mean it belongs in your product; pressure to be 'AI first' often degrades UX.
ai-uxexcalidrawwhiteboarding
Original description
Covid sent everybody home and created the space of virtual whiteboards. At first the experience reused the physical constraints but soon it became better than a physical whiteboard thanks to using virtual native concepts like copy-paste and using keyboard input. The next step in this evolution is to integrate AI into the workflow. We've tried a lot of things with Excalidraw and ended up landing on turning prompt into diagram. Come to the talk to understand how it fits into the workflow and how we implemented it. About Christopher Chedeau Co-creator of React Native and Prettier. Creator of Excalidraw, "CSS-in-JS", Yoga and React Conf. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter