AI Agent

Use the AI Agent activity to build an Al agent that can solve tasks defined in the prompt and instructions, and can execute other pre-selected workflows. This allows workflows to combine agentic and deterministic automation to maximize autonomy and control.

Warning: The AI Agent activity can execute workflows until the task is complete. When nested within another agent, this may result in unintended loops or repeated executions. Ensure that you review which workflows the agent is allowed to execute in the Tools area when configuring this activity and thoroughly test the workflow before you mark it as Production Ready.

After you run a workflow

Usage

Complete the following properties to use this activity:

  • Request - Specify the following information or click the Variable Reference icon to choose a variable:

    • Model - Choose the OpenAI model that will process the requests. The list of models is updated as new models become available. The default model is GPT-5.

    • System instructions - Enter the informational instructions (such as role, context, and constraints) used by the system to process the requests. This shapes the tone, focus, and constraints for all responses in this workflow. For example, act as a cybersecurity analyst.

    • User prompt - Enter the prompt to ask AI to generate a response to your questions. You can reference from inputs or incident data to make the requests more dynamic. For example, paste in the incident details and prompt the AI to summarize the incident.

  • Agent Configuration - Specify the following information or click the Variable Reference icon to choose a variable:

    • Agent name - Enter a name for the AI agent. When you execute this workflow, the agent name will appear in the Started by column on the Runs page. For more information, see View, Filter, and Search for Runs.

    • Maximum agent turns - Enter the maximum number of turns the AI agent will provide responses. This is helpful to prevent infinite loops with the AI agent, which may cause an increase in tokens and billing costs. By default, the maximum is set to 30 turns.

  • Tools (workflows) - Specify the following information:

    Note: You must specify a minimum of one workflow or workflow category to include. Use the Ask AI activity if you do not want to use workflows. After you run a workflow with the AI agent activity, you can view the workflows executed and links to the runs on the Runs page.

    • Specific workflows to include - Select specific workflows to use during the execution of the workflow by the AI agent. Otherwise, no workflows are included. The AI agent waits for the selected workflows to complete. If the workflows do not finish by the defined timeout period, the agent will time out. Only Production Ready workflows are included.

    • Workflow categories to include - Select the workflow categories to use during the execution of the workflow by the AI agent. Otherwise, no workflow categories are included. The AI agent waits for the workflows in the selected categories to complete. If the workflows do not finish by the defined timeout period, the agent will time out. Only Production Ready workflows in the selected categories are included.

  • Advanced Configuration - Specify the following information or click the Variable Reference icon to choose a variable:

    • Temperature (chat response variability) - Enter the variability of the AI responses, between 0 and 2, that controls creativity versus consistency in the AI answers. The lower the value, the output is more deterministic, focused, and consistent. The higher the value, there is an increase in the variability and creativity of the output. We recommend that you use a lower value for factual tasks. The default temperature is 1.

      • 0 - A precise variability that produces highly deterministic and focused responses, with minimal randomness. Best for scenarios where accuracy and predictability are critical. This can be used for fact-based outputs, summaries, or any context requiring strict adherence to the prompt.

      • 1 - A balance between creativity and focus. Outputs are still grounded but allow for some variety and flexibility. This can be used for general purpose conversations, moderate creativity, and informative responses.

      • 2 - A creative variability that encourages more creative and diverse outputs. It adds a level of randomness while still maintaining coherence. This can be used for brainstorming ideas, generating varied responses, or exploring multiple possibilities.

    • Previous response ID - Enter the identifier used by AI when returning a response. This is used for debugging or tracking specific AI interactions in audit trails.

    • Structured output - Click Add to specify the JSON format for the AI model to use in the text responses. Enter the JSON key in the Field name field and choose the output data type in the Field type drop-down list (bool, integer, number, or string).