For AI agents: the complete documentation index is available at /llms.txt, the full documentation bundle is available at /llms-full.txt, and this page is available as Markdown at /get-started/web-playground-chatgpt.md.
  • English

      • Get started: Web · Playground · ChatGPT subscription

      These are the setup steps for Midscene on Web with Playground and a ChatGPT subscription. To choose another combination, change the answers below or see all setup paths.

      Which platform do you want to automate?
      What do you want to do first?
      How will you connect a model?

      Step 1

      Install the Chrome extension

      1. Install Midscene from the Chrome Web Store:

        Available in the Chrome Web Store

      2. Open Midscene from the Chrome extensions list. The Midscene sidebar appears on the right side of the browser.

      If you cannot access the Chrome Web Store, see Can I install the Chrome extension manually?

      Step 2

      Sign in with your ChatGPT subscription

      1. In the Midscene sidebar, click the settings icon to open the model configuration dialog, then click Use your ChatGPT plan and follow the on-screen instructions to sign in and authorize plan usage.
      2. Paste the following configuration into the same dialog:
      MIDSCENE_MODEL_AUTH_MODE="siwc"
MIDSCENE_MODEL_NAME="gpt-6-sol"
MIDSCENE_MODEL_FAMILY="gpt-6"
      1. Click Verify to test the connection. For failed checks, see Model advanced configuration and debugging.

      Available models depend on your ChatGPT account. For credentials and usage, see Use a ChatGPT subscription.

      Step 3

      Run an action and verify the result

      Open TodoMVC in the current tab and keep the page visible.

      1. Select aiAct in the side panel, enter the following instruction, and run it:
      Add a todo named "Try Midscene", then mark it as completed.
      1. Once the completed todo item appears on the page, switch to aiAssert, enter the following assertion, and run it:
      The list contains a todo named "Try Midscene", and it is marked as completed.

      1. Confirm that the assertion passes and inspect the step-by-step screenshots in the results panel.

      2. (Optional) Switch to aiQuery, enter the following query, and run it:

      Return the visible todo items as {name: string, completed: boolean}[].

      The result contains each todo item's name and completion status. aiQuery extracts data from the current UI without changing the page.

      If execution fails, inspect the failed step and error message. For model request errors, see Verify model connectivity and Common configuration errors. For extension errors when accessing a page or Ollama, see the Web FAQ.

      Step 4

      Next steps

      • Explore more examples: Showcases includes demo videos and full execution reports across platforms.
      • Learn how Midscene works: The Basics explains the vision-based approach and when to use aiAct, instant actions, and insight APIs.

      Want to try another platform or way to use Midscene? Back to top to change your selections.