Example prompts for the Autopilot agent experience, including automation generation, test creation, and API workflow operations.

This page collects example prompts for the Autopilot agent experience. For prompting best practices, refer to the Prompting guide.

You can instruct Autopilot in Test Manager to evaluate requirements from various perspectives such as user flow, consistency, relevance, clarity, completeness, and security, and then generate the top ten enhancement suggestions. You can also use Autopilot to perform specialized analyses focused only on:

You can also provide Autopilot with supporting documents, such as security guidelines, accessibility guidelines, audit reports, user accessibility specifications, and compliance checklists, to enhance the description of a requirement.

You can use out-of-the-box prompts from the Prompt Library in Test Manager to help analyze your requirements, and you can also add your own custom prompts to the Prompt Library, for future requirement evaluations.

Refer to Best practices and limitations to check the best practices and guidelines available for evaluating requirements.

Autopilot in Test Manager uses AI to generate test cases and relies on the specificity of requirement descriptions. This includes the following components:

Ensuring the specificity of requirement descriptions allows Autopilot to generate accurate and detailed test steps. You can also give Autopilot additional instructions, whether for end-to-end flow verification or rapid test idea generation, among others, to tailor the test case generation for certain scenarios.

You can provide supporting documents, such as process diagrams and mockups, compliance documents, and discussion transcripts, to give Autopilot additional context to generate more accurate and relevant test cases.

You can use out-of-the-box prompts from the Prompt Library in Test Manager to help generate manual tests, and you can also add your own custom prompts to the Prompt Library, for future test generations.

Refer to Best practices and limitations to check the guidelines and best practices available for generating test cases using Autopilot.

To convert text into code, you can offer Autopilot instructions about generating any C# code, refactor existing code, or generate a UiPath automation.

For more information, refer to Best practices and limitations.

To convert manual test cases into automation, you need a consistent object repository, because Autopilot uses UI Automation capabilities to reference UI elements. It's important to maintain a consistent naming convention for UI elements within manual steps to ensure that the generated automation is relevant. You should also use common activity names in manual steps so they can be easily converted into corresponding UiPath APIs in Studio Desktop.

For more information, refer to Best practices and limitations.

When you generate synthetic test data, Autopilot considers the existing arguments within your workflow and the additional instructions provided in the prompt to generate test data. You can also provide instructions to follow a certain combination of data, or to customize your data set.

For more information, refer to Best practices and limitations.

Autopilot in Test Manager provides insights into failed test cases and recommendations for reducing the failure rate in your test portfolio. The more test results you provide, especially with failed test cases, when you generate the report, the more effective it is. The goal of the test insights is to help understand the main reasons why your tests are failing.

Each section within the report displays information about a certain area of your test results, such as:

Autopilot uses a proprietary tool, the API Workflow Assistant, to generate, edit, and analyze API workflows based on your input.

Depending on the complexity of your workflow, you can prompt specific instructions, such as:

When you prompt Autopilot to generate a workflow, it analyzes your request, activates the API Workflow Assistant to design the workflow structure, identifies necessary API calls, determines action sequences, and anticipates data flow. If details are missing, Autopilot may ask clarifying questions. It then generates a preview for your review.

When you ask Autopilot to edit a workflow, it parses your request, locates and modifies specific activities, parameters, or logical blocks, ensures data consistency, and generates an updated preview for your review.

When you prompt Autopilot to analyze a workflow, it extracts specific information, diagnoses potential issues, and provides insights into the workflow structure, logic, and performance.