OpenAI has introduced a new “Canvas” interface for ChatGPT, allowing users to customize text or code generated by the chatbot in a parallel collaboration. Canvas opens a separate editing window next to the existing ChatGPT chat box, which can be used to manually modify text or code, or to highlight specific sections to better accommodate ChatGPT’s editing suggestions and feedback.

“Canvas allows ChatGPT to better understand the context of what you want to achieve,” OpenAI said in its announcement. “To make AI more useful and accessible, we need to rethink how we interact with it. Canvas is a new approach and the first major update to ChatGPT’s visual interface since our launch two years ago.”

The ChatGPT canvas provides users with a menu of shortcuts to suggest inline edits, quickly check grammar and clarity, and adjust the length and reading level of the text. Some program-specific keyboard shortcuts are also available for debugging, adding logs and comments, and translating code into other languages. It’s a similar concept to the Artifacts feature that rival AI developer Anthropic introduced for Claude in August.

Previously, ChatGPT users typically had to repeatedly enter new prompts to refine what the chatbot was spitting out. Canvas sounds a lot less boring and gives users extra control. It offers a back button to restore previous working versions, and OpenAI says it optimizes when Canvas activates automatically – for example, reducing the likelihood of it triggering during coding tasks to avoid annoying power users avoid.

The Canvas interface is currently in beta and can be accessed by selecting “GPT-4o with Canvas” from ChatGPT’s Model Selection drop-down menu. It’s rolling out globally to ChatGPT Plus and Teams users, with access expanding to Enterprise and Edu users next week. Once the beta period is complete, Canvas will be available to ChatGPT’s free users and will open automatically “when ChatGPT detects a scenario in which it could be helpful,” OpenAI said.