- Getting started
- Best practices
- Data privacy
- Autopilot chat
- Generating automations
- Generating tests
- Generating tests
- 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 coded automations
- Generate coded API automation
- Refactor coded automations
- Generate low-code automations
- Generate synthetic test data
- Generate test reports
- Search Test Manager project
- Troubleshooting Autopilot for Testers
- 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
- Troubleshooting
Autopilot capabilities for generating, refactoring, and analyzing test cases in Test Manager and Studio, including licensing requirements and product-level limitations.
Overview
Autopilot for testers accelerates the testing lifecycle by generating, refactoring, and analyzing test cases from natural language prompts. With a single prompt, you can create or modify manual, low-code, or coded test cases directly in Test Manager or UiPath Studio.
This experience is non-conversational: you provide one prompt and Autopilot returns the result, without switching contexts. It integrates into the testing tools you already use, helping teams design test cases with less manual effort.
On Automation Suite, Autopilot for testers is available only when Test Manager is delivered through Test Cloud (EKS/AKS and OpenShift installations). On cloud, availability varies by capability — see the Test Manager feature availability page.
For the models Autopilot supports, visit Supported models and limits.
For an interactive, context-persistent, and chat-based experience, use the Autopilot chat. It offers similar generative capabilities, and allows you to refine tests, analyze failures, or explore results iteratively through natural conversation.
To access the test generation capabilities, you first need to enable the Autopilot capabilities in Studio and Test Manager. For information on enabling and disabling Autopilot capabilities, visit Enabling/disabling Autopilot.
Where test generation capabilities are available
Autopilot for testers is available in two products, each covering a different part of the testing lifecycle:
| Product | Autopilot capabilities |
|---|---|
| Test Manager | Generate, import, and manage manual test cases; evaluate requirement quality; find obsolete tests; analyze test results; and search test assets using natural language. |
| Studio | Generate, refactor, and enhance coded test cases, low-code tests, and API-based tests. |
These integrations bring AI-powered testing assistance directly into the tools you already use for design, execution, and maintenance, keeping the testing lifecycle consistent and fast.
Capabilities
Autopilot can help you:
- Evaluate requirements for quality aspects such as clarity, completeness, and consistency in Test Manager.
- Generate manual test cases and test steps for requirements and supporting documents in Test Manager.
- Import manual test cases from Excel files directly into Test Manager, retaining key data such as title, description, and properties.
- Identify test cases that may no longer be relevant to an updated requirement.
- Generate manual test cases for SAP transactions in the Heatmap, and impacted transactions in Change Impact Analysis.
- Generate coded test cases from text or manual tests.
- Enhance existent coded automations using refactoring.
- Generate low-code test cases from text or manual tests.
- Generate coded test cases that employ APIs.
- Generate test data for your automations.
- Gain insights into why test cases are failing, without the need for pre-built reporting templates in Test Manager.
- Search any test object within a project, using natural language, and perform actions on the results.
Generating tests
Use the following topics to generate, refactor, or analyze test cases with Autopilot in Test Manager and Studio:
Test Manager
- Quality-check requirements
- Generate tests for requirement
- Import manual test cases
- Find obsolete tests
- Generate tests for SAP transactions
- Generate test reports
- Search Test Manager project
Studio
- Generate coded automations
- Generate coded API automation
- Refactor coded automations
- Generate low-code automations
- Generate synthetic test data
If a capability does not behave as expected, refer to Troubleshooting Autopilot for testers.
For best practices when working with these capabilities, refer to Best practices and limitations.
Licensing
The following Autopilot for testers capabilities are metered and subject to licensing:
- Generate test cases
- Import test cases
- Evaluate quality of requirements
- Generate reports
- Find obsolete test cases
Finding obsolete test cases is available in Test Manager only when delivered through Test Cloud.
Limitations
Autopilot for testers has the following product-level limits:
- Requirement input capacity - When you evaluate the quality of a requirement, its description and supporting documents must not exceed 128,000 tokens (approximately 96,000 words), or 512,000 characters.
- Requirement-quality suggestions - Autopilot generates a maximum of 50 suggestions per evaluation. If you don't specify a number, Autopilot generates the top 15 suggestions.
- Test case steps - You can generate test cases with a maximum of 50 steps.
- Supported file types - You can upload the following file extensions when using Autopilot for testers:
- Processes only text content – TXT, BPMN, CSV
- Processes both text and image content – DOCX, XLSX, PNG, JPG, PDF
Refer to Supported models and limits for the context-window and output-token limits that apply to the underlying model.