- Getting started
- Capabilities
- Data privacy and governance
- Product availability
- Earlier Autopilot capability sets
- User scenarios
- Prompting guide
- Example prompts
- 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
- 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
Guide to writing effective prompts for generating accurate automations with the Autopilot agent experience.
This guide helps you write effective prompts and prepare necessary resources for creating accurate workflows with the Autopilot agent experience.
For general prompting tips, refer to Writing effective prompts.
Provide clear, individual instructions
Break tasks into small, clear actions. Autopilot generates accurate sequences when prompted with concise, separate steps.
Prompt examples
- "Log into ACME, download a file, and email it."
- For an If-Else activity: "If username and password are empty, log message "Not able to extract credentials from asset". Else log message "credentials details are extracted correctly"."
Prepare the Object Repository for UI Automations
- Define the UI elements in the Object Repository first. Otherwise, the UI automation may fail.
- Ensure elements have accurate names and context, to help Autopilot semantically match elements.
Pre-create Orchestrator assets
Assets are shared variables or credential resources in Orchestrator. Make sure assets already exist in an Orchestrator folder before using them in an automation, as Autopilot cannot create assets dynamically.
Prompt examples
- Vague: "Use the credentials to log in."
- Better: "Get values from the ACME credential asset."
- Best: "Get values from the ACME_credential asset, which is in the Test folder in Orchestrator."
Pre-create Orchestrator queues
Queues are containers that allow you to hold an unlimited number of queue items. Make sure queues exist in an Orchestrator folder before using them in an automation, as Autopilot cannot create queues dynamically.
Prompt examples
- Vague: "Use the queue to insert data."
- Better: "Insert transaction into queue ACMELoan."
- Best: "Insert transaction into queue ACMELoan, which is in the Test folder in Orchestrator."
Specify activities explicitly
Clarify which activities to use. Autopilot favors activities previously used in the current workflow.
Prompt example
- Explicit: "Send an email using UI Automation, not Outlook."
Understand Autopilot limited context
Autopilot recognizes only the resources in the current file:
- Variables defined in the current file.
- Activities previously used in the current workflow.
- Assets and packages available via Data Manager.
Autopilot cannot access:
- Other workflow files.
- Global variables.
- The full project structure.