ChatGPT dots follow custom instructions and reply faster

ChatGPT dots now follow custom instructions, and OpenAI says they reply faster, use less jargon and follow through better.

Tell your dot in its thread how to behave or which actions need your go-ahead, such as "always talk in lowercase" or "show me a draft before sending." It keeps that as an ongoing instruction, and you can ask it to update one later. On mobile, where Behavior is available, you can review and edit them under Customize > Behavior. A dot's instructions are separate from your ChatGPT custom instructions.

Custom rules are still there for specific action boundaries, under Settings > Personalization > Custom rules on desktop and web. Neither instructions nor custom rules override built-in safety requirements, and asking your dot to draft replies doesn't give it permission to send them.

Dots are rolling out gradually to Pro 100, Pro 200 and Pro 500 users aged 18 and older outside the European Economic Area, the UK and Switzerland, and to eligible Business Premium workspaces. They are also in eligible Enterprise, Edu and Healthcare workspaces, where access turns on by default from November 18, 2026 unless the workspace opts out.