OpenAI has announced Intelligent UI, a new ChatGPT feature that enables it to create interactive visual interfaces. Rolling out this week alongside GPT-6‘s wider release, Intelligent UI is intended to make the AI chatbot’s responses more visual so they’re easier for users to understand.
“We’ve trained GPT‑6 to compose responses using text, visuals and interactive elements, choosing how they fit together based on your question,” OpenAI wrote in its announcement on Wednesday. “With Intelligent UI, responses can include graphics, tappable buttons, forms, charts, and interactive experiences you can use directly in your conversation.”
Exactly what type of graphics ChatGPT will use will depend upon the prompts users provide. The AI chatbot will still provide text-only responses when that is the most suitable format to respond to input. However, OpenAI indicated that ChatGPT could now provide an interactive diagram of a bicycle to explain its design, or create a graph to explain GDP. Intelligent UI will also allow ChatGPT to create tools for tasks, such as generating a calculator to split a bill, or for projecting your future retirement savings.
Mashable Light Speed
Credit: OpenAI
To develop Intelligent UI, OpenAI built a collection of components its AI model could pull from when building interactive visual content. The model was then trained to use these components to generate responses suitable for different prompts.
“GPT‑6 learned to use the component library and make good design decisions, including how to organize information clearly, when to use interactivity, and when a simple text response is enough,” wrote OpenAI.
OpenAI’s GPT-6 model launched for paid ChatGPT in September, replacing GPT-5.6 as the model powering the AI chatbot. However, last month’s rollout did not include Intelligent UI. This feature will now be available to users on ChatGPT’s Plus, Pro, Business, and Enterprise tiers from Wednesday, subsequently rolling out to Free and Go tiers from Thursday as they also transition to GPT-6.
Disclosure: Ziff Davis, Mashable’s parent company, in April 2025 filed a lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.
