- 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
Autopilot as a coding agent for Maestro Flow projects in Studio Web: what you can do and the tools it uses.
Autopilot in Studio Web builds and edits Maestro Flow projects using natural language — the same coding agent that ships with Studio Desktop, adapted to the Flow project type.
Use Autopilot to:
- Build a flow from a plain-language description — plan the node sequence, then scaffold it.
- Add and configure nodes: connector activities, approval steps, script steps, subflows, IXP document-extraction nodes, and Data Fabric entity nodes.
- Wire triggers and schedules, and build conversational flows for chat, chatbot, voice, or phone calls.
- Wire a node to an existing published process, agent, or connector instead of building a duplicate.
- Validate and format a flow, then run a real end-to-end debug session.
- Publish a flow to Orchestrator or push it to Studio Web.
- Manage a deployed flow — trigger it, inspect jobs and traces, and pause, resume, cancel, or retry instances.
- Diagnose a failed or misbehaving run from its incidents, variables, and traces.
- Design evaluation sets and evaluators, run Studio Web evaluations, and compare results across runs.
Tools
Before making changes, Autopilot reads the Maestro Flow skill for the open project, plus the human-in-the-loop skill for approval steps. It uses the flow and maestro UiPath CLI (uip) command groups to scaffold, validate, format, debug, and publish the flow. The same command groups manage deployed runs and evaluations.
Before adding a node for a named external service, it looks up existing connectors and published processes or agents first. This way, it reuses what already exists instead of building a duplicate. Running a debug session executes the flow for real — sending emails, posting messages, or calling APIs — so Autopilot asks for your confirmation first.
It also uses the platform skill for connections, connector activities, assets, queues, and jobs. It can read, edit, and search project files, and create new Flow projects at the solution level.
Known limitations
You can switch back to the classic Autopilot experience from the chat title bar at any time — for Flow projects, the classic experience provides the generic set of tools only (web search and documentation search, no project-specific tools).