Co-Pilot for Automators

Co-Pilot for Automators (Co-Pilot) is an on-demand, intelligent automation assistant. Accelerate development by describing goals in natural language for Co-Pilot to create and update automation.

Co-Pilot for Automators leverages the capabilities of generative AI (gen AI) to transform and simplify the development experience of automation. This intelligent assistant allows developers to express their automation goals in plain language, eliminating the need to navigate complex interfaces. Co-Pilot efficiently translates these goals into optimized, compliant automated processes and task bots, enhancing return on investment and scaling automation programs with ease.

Traditionally, building automation requires manually selecting nodes and actions, a time-consuming task. Co-Pilot streamlines this human effort with natural language instructions that leverage gen AI and Large Language Models (LLM) to make development intuitive and efficient. Key areas where Co-Pilot shines include task sequencing and mapping input data, providing developers with the collaborative power of gen AI during construction of enterprise-level automation. This collaborative assistance quickly delivers and sequences the described building blocks of your automation and attaches inputs, seamlessly within the Automation Workspace. This tool not only accelerates development but also ensures that automations are built with precision and adaptability, making it an invaluable asset in a developer's toolkit.

Interfacing with Co-Pilot for Automators

Co-Pilot is designed to be highly functional, non-intrusive with low cognitive load. It is embedded directly within the Automation Workspace, as a page in the Assistant widget.

Functionality is tailored to developer needs, staying mindful of common practices. The following principles ensure Co-Pilot offers maximum efficiency and ease-of-use.
  • Co-Pilot page offers an embedded conversational experience for building automation with natural language.
  • Functionality ensures low-learning curve for quick adoption.
  • Built-in guardrails with enterprise-tuned AI models only allow Automation 360 tasks.
Co-Pilot has flexible viewing options to be readily available while providing assistance only when needed. The interface offers multiple views to ensure it complements your development process.
  • The floating view displays the widget, with adjustable size.
  • Dock the interface as a side-panel for more comprehensive usage and reference during sophisticated development.
  • Minimizing the interface is convenient way to retain your conversation until the interface is closed.

The conversational experience is optimized to be intuitive without your fingers leaving the keyboard, making it easy to create and call variables, reference inputs, and make edits to automation. Co-Pilot responds to prompts with interactive messages that offer status and guidance on changes as you develop your automation. See, Response messages from Co-Pilot for Automators

Note: Generative AI models can produce errors and/or misrepresent the information they generate. It is advisable to verify the accuracy, reliability, and completeness of the content generated by the AI model.

Use cases

Developers can overcome common challenges and accelerate development by articulating scenarios in natural language. Co-Pilot for Automators can assist in selecting, sequencing and configuring items of the automation to reach development goals. Consider the following use cases when and where Co-Pilot for Automators is highly impactful in saving time and effort.

Process Composer Prompting for a process
  • Create the complete automation or select and edit part of the process.
  • Add a new task (Process, Bot, Form, API, Approval) to the end, or a selected location, of the process and map dependencies.
  • Add a learning instance from Document Automation to the end of the process. Support for learning instance in a process
  • Set the conditions of dependencies.
  • Update one or multiple supported properties of an existing node.
Bot editor Example of prompting for a task bot
  • Create the complete automation or select and edit a part of the bot.
  • Add a new action to a selected location of the automation. When adding an action, variables for mandatory attributes are automatically created.
  • Update properties of one or multiple selected actions. Update automation via select and prompt
  • Create and reference variables to edit properties.
  • Add and update the conditions of if/else actions.
  • Set the iterator type and items of loop logic (for, while). Prompting for loops

Availability

An Automator AI Platform Base license is required to enable Co-Pilot for Automators capability. A license is available to all Cloud tenants. With the license assigned, options are available to enable capabilities to a tenant and a role. Admin can enable the feature for tenants through Control Room settings. Configure Settings

When enabled, Co-Pilot is accessible to users with:
  • Minimum of one developer role assigned: AAE_Basic or AAE_Bot Developer
  • A user-created role with the Co-Pilot for Automators permission set assigned. Feature permissions for a role
  • An assigneddevice license: Bot Creator or Citizen Developer.
Note:
  • Co-Pilot for Automators is optimized for use in English. There might be limited functionality in other languages.
  • This capability is powered by an ensemble of AI/ML and large language models (LLM), and requires specific data attributes to be sent to sub-processors for completing the user requests. See Automation Anywhere Data Processing Addendum for details.
  • For more information see Data security for generative AI - FAQ.
  • For details about the Automator AI Platform Base license, see Automator AI Platform Base.