What is generative UI?
Generative UI is interface that an AI generates or assembles on the fly in response to a task, rather than being hand-built in advance. Instead of navigating fixed screens, a user states a goal and the system produces the controls, layout, or visualization that fits the moment.
Understanding generative ui
Traditional software ships a fixed set of screens a designer built ahead of time. Generative UI flips that: the model composes the right interface for the task at hand — a form, a chart, a canvas of options — so the interface adapts to the user instead of the user adapting to it.
It pairs naturally with agents: the agent reasons about what the user is trying to do, then renders the surface that helps most. A design tool might generate a comparison of variants; a data tool might assemble the exact dashboard a question needs.
The building block is still real, editable output — components and vectors the user can keep refining — not a static screenshot.
A canvas agents can see
The read/write canvas agents perceive and drive.
Keep exploring
AI agent
An AI agent is a system that uses a language model to pursue a goal across multiple steps — planning, calling tools, observing results, and adjusting — rather than producing a single response. Agents can read data, run code, generate assets, and act in software on a user’s behalf.
Context engineering
Context engineering is the practice of deciding what information a model sees at inference time — which documents, memories, tools, and instructions to place in the context window — so it produces accurate, grounded output. It has largely superseded "prompt engineering" as models and context windows have grown.
The design workspace where these ideas are real
Agents that generate, a canvas they can see and drive, and a brain that keeps every asset on-brand. Free to start.