Generative UI for agents

Agents respond with interactive interfaces that use forms, charts, and layout components suited to the conversation.

Agents can respond with interfaces that match the task instead of returning only text. OpenUI Cloud validates and streams each response so it renders live in the application. Use the built-in component library or bring your own.

Built-in component library

OpenUI Cloud includes a pre-tested, responsive, and accessible set of components for forms, inputs, charts, content organization, and interactive actions.

Forms and inputs

Form components include text fields, selects, options, and defaults. They compose into forms that collect structured input in one step instead of over several text messages.

Charts and visualizations

Interactive chart components include pie, bar, line, area, and radial charts. Agents can select the format that matches the data, such as pie charts for shares, bar charts for comparisons, and line charts for trends.

Content organization

Layout components include tabs, accordions, tables, and cards. They organize long responses into scannable sections, such as alternatives in tabs, details in accordions, and comparisons in tables.

Buttons and actions

Action components include buttons and controls for next steps such as confirming, booking, or refining. Interactions feed back into the conversation as structured events instead of typed commands.

Bring your own component library

Connect your own design system and domain-specific components. Agents can use them to generate interfaces while OpenUI Cloud provides model reliability, output validation, and observability.

On this page