Latenode

OpenAI adds Chrome control to ChatGPT for signed-in web tasks

Builders get a documented way to automate logged-in browser tasks and extract info from active tabs. The tradeoff is permission scope, so approval steps and limited access should be part of the workflow design from the start.

OpenAI adds Chrome control to ChatGPT for signed-in web tasks

OpenAI has documented a Chrome extension that lets ChatGPT control Chrome and read or act on sites where users are already signed in. The OpenAI guide says setup starts in the desktop app, with tasks launched through ChatGPT Work or Codex; availability can vary by rollout and workspace settings.

The extension can pull in context from open tabs and keep browser tasks grouped in Chrome tab groups. OpenAI also distinguishes the desktop app’s @Browser from browser-specific control through mentions such as @Chrome. The Verge reported demos showing multi-tab comparison and prompts for compiling vendor details, pricing, features, and source links.

OpenAI says the extension may request broad permissions covering website data, history, downloads, bookmarks, and tab groups. Per-site approvals and allow/block lists add controls, but workflows touching sensitive accounts still need narrow access and human checkpoints.

When models and APIs shift keep the workflow running

Connect the models and apps from stories like this in one scenario. If a vendor changes routing, pricing, or availability, you update the workflow — you don't start over.

Start Free

Free forever plan. No credit card required.