concept

Generative UI

Generative UI is the pattern where a language model dynamically chooses, configures, and renders UI components in real time based on the user's intent — instead of returning text, it returns a UI.

Pioneered by Vercel's AI SDK in 2024 and now broadly adopted, generative UI replaces "chatbot returns text" with "chatbot returns UI components". The model decides whether to show a chart, a form, a card, a map, or a table — and provides the data. The harness renders the components using your design system. This is a major UX shift in chat apps because the model can answer with appropriate interactive surfaces instead of forcing users to read text. Production implementations use function calling or structured output to constrain which components the model can emit.

When to use generative ui

Common mistakes

FAQ

What is generative ui?

Generative UI is the pattern where a language model dynamically chooses, configures, and renders UI components in real time based on the user's intent — instead of returning text, it returns a UI.

When should I use generative ui?

Chat interfaces that visualise data. Conversational dashboards. Assistant interfaces for non-text outputs.

What are the most common mistakes with generative ui?

Letting the model pick any component — too many choices degrade reliability. Skipping schema validation on the rendered component args.

Last updated: 2026-06-01. Raw markdown: https://promtable.com/glossary/generative-ui.md.