- 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
- 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
Recommendations for writing clear prompts and engaging with Autopilot responses.
Autopilot is designed to help you build, edit, and troubleshoot automations through a conversational experience. To get the most out of it, follow these recommendations to craft prompts, respond to suggestions, or manage your interactions:
Writing clear and specific prompts
Type your request in the chat input field. The more specific you are, the better Autopilot can understand and respond to your needs:
- Example: "Build a workflow that reads emails from Outlook, saves attachments, and logs the filenames in Excel."
- Too vague: "Help with email."
You can also reference existing elements from your project, for example "Update the UploadFiles sequence to include error handling."
Selecting model effort
Most models available by default in Autopilot support multiple effort levels, ranging from Very low to Extra high, depending on the selected model. The effort level controls how much reasoning the model applies when working through your request.
- Higher effort levels allow the model to reason more thoroughly, which can improve results for complex tasks, such as developing and debugging automations, but may increase response times.
- Lower effort levels generally produce faster responses and can be suitable for simpler tasks.
When you switch models, Autopilot automatically adjusts the effort level to the corresponding level supported by the new model, preserving your previous selection as closely as possible. By default, Autopilot uses Extra high or High, depending on the default model. Internal testing shows these effort levels deliver the best results for automation development.
Engaging with follow-ups and proposed solutions
Autopilot may guide you through the task by:
- Asking follow-up questions to clarify intent.
- Suggesting a step-by-step solution for you to accept or reject.
- Offering multiple options for how to complete a task.
Managing conversation history
Autopilot saves your conversations, allowing you to revisit and continue past sessions.
- Use the Chat History panel to browse or search previous conversations.
- Select a conversation to pick up where you left off, as Autopilot retains full context.
- Delete conversations you no longer need by selecting them and choosing Delete.
Starting a new chat
If you want to switch to a different task, select New Chat in the Autopilot header. This starts a clean session and ensures previous context does not interfere with your new request.