Execute AI Agent Smart Service

Overview

The Execute AI Agent smart service allows you to run a configured AI agent from within a process model. This enables you to seamlessly integrate generative AI capabilities into your automated workflows, passing data to the agent and receiving structured output.

Properties

The Execute AI Agent smart service is configured using the following properties.

Data tab

The Data tab contains all the configuration options for running your AI agent. Use the Inputs section to specify which agent to execute and what data to provide, and the Outputs section to capture the results returned by the agent.

Inputs

The Inputs tab allows you to configure which AI agent to run and what data to provide as an input.

• Agent UUID (Integer): The UUID of the AI agent you want to run.

  Tip:  You can find the agent's UUID on the AI agent design object, under the Properties menu.

• Agent Inputs (Map): A map of key-value pairs to pass as inputs to the AI agent. The keys must match the input variable names defined in the AI agent's configuration. For example:

  1
  2
  3
  4
    a!map(
       orderFormDoc: pv!orderFormDocUpload,
       agentRunUuid: pv!agentRunUuid
    )
  

  Note:  Agent Inputs does not support a list of maps.

Outputs

When your AI agent is configured to output structured data, the process model stores these outputs in a process variable. You can access the results from the Outputs pane on the Data tab.

• Agent Outputs (Map): A map containing the structured data returned by the AI agent. The keys in the map correspond to the output variable names defined in the AI agent's configuration. To access an individual value, you can use a script task to index into the map and save the value to a separate process variable.
• Run Summary: Provides a brief summary of the entire AI agent run.
• Run ID (Text): A unique identifier for the AI agent run. Use this ID to track and reference specific agent runs for monitoring or troubleshooting purposes.

Example: Outputting a record type

You can select a record type as an AI agent output. The AI agent automatically determines which fields are relevant based on context. If you need the AI agent to populate specific fields, be sure to include them in the AI agent's instructions.

Usage Considerations

• Any inputs provided on the Inputs tab that are not defined in the AI agent configuration are ignored.
• The AI model is prompted to provide all required outputs defined in the configuration, but this is not guaranteed on every run.
• Appian does not validate whether all required outputs are present in the AI agent's response before completing the run.
• Output data types are validated. If an output value from the AI agent cannot be cast to the configured data type, the smart service will fail.
• The smart service does not support MNI execution (Multiple Node Instances)
• When AI Guardrails are enabled and a Block action triggers during an agent run, the agent receives the administrator-configured block message and proceeds with different content. The agent does not stop or fail due to a guardrail block.

Feedback