- Getting started
- Capabilities
- Data privacy and governance
- Product availability
- Earlier Autopilot capability sets
- User scenarios
- Prompting guide
- Example prompts
- Autopilot usage pool for testing
- Best practices and limitations
- Supported models and limits
- Quality-check requirements
- Generate tests for requirement
- Import manual test cases
- Find obsolete tests
- Generate tests for SAP transactions
- Generate synthetic test data
- Generate test reports
- Generate coded test cases
- Search Test Manager project
- Troubleshooting
- Troubleshooting
- Troubleshooting Autopilot
- Autopilot for Everyone
- About Autopilot for Everyone
- Licensing
- User types
- Data sources
- Toolset automations
- Localization
- Prerequisites
- Autopilot widget
- The Autopilot for Everyone tenant card
- Prerequisites for installation
- Enabling Anthropic models
- Installing Autopilot for Everyone
- Updating Autopilot for Everyone
- Uninstalling Autopilot for Everyone
- Configuring Autopilot for Everyone
- Disabling the Autopilot welcome screen in Assistant
- Configuring an LLM for Autopilot for Everyone
- Deploying toolset automations
- Prompt-to-response flow
- Launching Autopilot for Everyone
- Autopilot settings for business users
- Using a specialized Autopilot
- Using a starting prompt
- Uploading and analyzing files
- Running automations
- Interacting with Autopilot answers
- Using suggested prompts
- Starting a new chat
- Chat history
- Providing general feedback
- Clipboard AI Enterprise version
- Designing relevant automations for Autopilot for Everyone
- Troubleshooting
Troubleshooting Autopilot
Solutions for common Autopilot issues, including a blank chat view in the VS Code extension and Gemini model configurations that fail in Automation Suite 2025.10.
VS Code extension
The Autopilot chat view is blank
The Autopilot chat view opens, but it is blank and the message box is missing. Reinstalling the extension or switching to a new VS Code profile does not resolve it.
The Webview Developer Tools show the following error:
Webview fatal error: Error: Could not register service worker:
InvalidStateError: Failed to register a ServiceWorker:
The document is in an invalid state.
Error loading webview provided by 'UiPath.autopilot-vscode':
Error: Could not register service worker: InvalidStateError:
Failed to register a ServiceWorker: The document is in an invalid state.
Webview fatal error: Error: Could not register service worker:
InvalidStateError: Failed to register a ServiceWorker:
The document is in an invalid state.
Error loading webview provided by 'UiPath.autopilot-vscode':
Error: Could not register service worker: InvalidStateError:
Failed to register a ServiceWorker: The document is in an invalid state.
Cause: VS Code cannot start the panel that the Autopilot chat runs in, so the chat never loads. Panels from other extensions, such as Markdown preview, fail the same way until the cache is cleared. This is a known VS Code issue. For details, refer to microsoft/vscode#125993.
Solution: Clear the VS Code service worker cache:
-
Close VS Code fully. On Windows, select File > Exit, then end any remaining
Code.exeprocesses in Task Manager. -
Delete the
Service Workerfolder for your operating system. The folder contains only cached data.Operating system Folder Windows %APPDATA%\Code\Service WorkermacOS ~/Library/Application Support/Code/Service WorkerLinux ~/.config/Code/Service WorkerFor VS Code Insiders, use the same paths with
Code - Insidersinstead ofCode. -
Start VS Code and open Autopilot.
Bring your own model
A Gemini model configuration fails in Automation Suite 2025.10
When you add an AI Trust Layer LLM configuration for Autopilot with a Gemini model, such as gemini-3.1-pro-preview, the configuration test fails and you cannot save the configuration. The error message is similar to the following:
/v1/projects/<your-project-id>/locations/global/publishers/google/models/gemini-3.1-pro-preview:generateContent was not found on this server.
/v1/projects/<your-project-id>/locations/global/publishers/google/models/gemini-3.1-pro-preview:generateContent was not found on this server.
Cause: Some Gemini 3.x models are served only from the Google Cloud global location. The Google Vertex connector in Integration Service for Automation Suite 2025.10 does not support the global location. This affects configurations for both the Chat and Generation features.
Solution: Create a custom Google Vertex AI connector that calls the global location, then use it in your LLM configuration:
-
In Integration Service, select Build your connector to create a custom Google Vertex AI connector. For details, refer to Building your first connector.
-
In Connector Builder, set the base URL of the connector to the
globallocation:https://aiplatform.googleapis.com/v1/projects/{project.id}/locations/global/publishers/googlehttps://aiplatform.googleapis.com/v1/projects/{project.id}/locations/global/publishers/google -
Save and publish the connector.
-
Create a connection for the connector. Provide your Google Cloud project ID and your service account key in JSON format.
-
In your AI Trust Layer LLM configuration, select the custom connector and the connection.
-
Set the ID of the Gemini model you need.