Starter workflows for a ChatGPT dot that keeps an analysis current: rerunning on new data, flagging anomalies, tracking sources and updating figures for your review.
OpenAI describes a scientist's dot that learns the research question, reruns analyses as data arrives, investigates unexpected results and updates the figures for the paper. The same shape works for any standing question: a market you follow, a competitor, a literature you keep up with.
Point the dot at the folders and feeds that matter, ask for a reviewable output on a schedule, and keep publishing or sharing anything as ask first.
For a standing research question: the dot watches a data folder, reruns the notebook on each new file, flags anomalies and sends only the figures that moved.
On Business, Enterprise and Edu workspaces, content is not used to improve models by default. On personal plans you control it in your ChatGPT data settings. OpenAI says it does not train directly on a dot's proactive research or its notes to itself.
Your first dot is included with ChatGPT Pro and Business Premium at no extra cost. Enterprise, Edu and Healthcare workspaces get a beta that the admin has to switch on. Free, Go and Plus do not include dots at launch. Pro users in the EEA, Switzerland and the UK are excluded for now; Business Premium works in every supported ChatGPT region.
Starter workflows are original instructions written as starting points and labelled untested. Community members report what worked, and those results appear on each workflow page as they come in.
Sources: OpenAI, Introducing dots ↗ · OpenAI Help Center ↗. Reviewed September 30, 2026. Sundog is independent and not affiliated with OpenAI.