Popular talk #25
Beyond Components: Designing Generative UI for MCP Apps — Ruben Casas, Postman
Synced transcript
Follow the talk
Automated overview
What this talk covers
Ruben Casas from Postman argues that AI models can now write better frontend code than he can—his prompt to rewrite his blog produced a search box with blur animation and accessibility out of the box—yet most agent UIs still invoke static prebuilt components. He presents three levels of UI generation: static components (AG UI, Goose) passing props to predefined React elements; declarative UI where the model generates JSON or YAML for a rendering engine (e.g., Vercel's JSON Render), which he deems the current ideal balance; and fully generative UI where the model writes HTML, CSS, and JavaScript on demand, as in his weather agent that does so in one tool call. The key obstacle is trust, necessitating sandboxing, and MCP apps with their double iframe default are the best delivery mechanism. He likens today to early TV—radio shows with cameras—and predicts the future lies beyond components in collaborative human-agent interfaces on shared canvases, as seen with the Skeletro MCP app.
This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.
Generated highlights
Key moments
Ruben Casas calls early ChatGPT UI copy-pasting the 'poor man's bit coding' era.
Andrew Karpathy: "Interacting with this new computer is like talking to the terminal."
Netflix has long used server-driven UI with static components to create personalized homepages.
Ruben Casas' weather agent generated HTML, CSS, and JavaScript in one tool call with no prebuilt components.
"The first TV shows were radio shows with cameras, because they could not imagine what you could do with this new technology."
Skeletro MCP app creates a shared canvas for true human-agent collaboration beyond static UI.
These moment labels are generated from the unreviewed transcript and may contain errors.
Generated classification
Detected Q&A
Q: Why are agent UIs mostly static when models excel at generating UI code?
Podhood’s automated analysis classified these moments as Q&A. AI Engineer has not independently reviewed them.
Community discussion
Add context, evidence, or a useful disagreement
Build on the talk with an example, caveat, connection, or elaboration. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.
Make it useful: add one concrete point, then support it with context, evidence, an example, or a caveat. Your words stay exactly as written.