Agentic AI

Generate content using the Agentic AIClosed Artificial Intelligence. Technology that applies intelligence and automation to observe environments, detect anomalous behavior, and execute automated investigations. language model of the Riverbed Platform. This node runs Agentic AI queries in a runbookClosed An automated workflow that executes a series of steps or tasks in response to a triggered event, such as the detection of anomalous behavior generating an incident, a lifecycle event, or a manually executed runbook..

For how agents relate to the Skill Catalog and Chat, see Agents. For the older GenAI node tied to Riverbed IQ Ops Assist, see GenAI and Chat, Skills, and Riverbed IQ Ops Assist.

AI-Generation disclaimer

When using Generative AI technologies to create and generate content, the target audience must be aware that the content is AI generated. We recommend adding a disclaimer to the output of the content generated using the GenAI node. For example, appending "AI-Generated content".

Properties

Node Label: Type an informative name for the Agentic AI nodeClosed Individual components that make up a runbook automation, each performing a specific function such as data queries, transformations, logic, integrations, or visualizations.. You may keep the default name Agentic AI.

Debug: Select Debug to receive debug data when the node executes.

Agent

Select the agent you want to use to analyze the data. Choose one of these options:

  • Select An Agent: Pick a published catalog agent.

  • Riverbed Q: Use the default assistant, Riverbed Q.

  • From Variable: Resolve the agent from a runbook variable.

An Agentic AI node requires an agent selection before the runbook can run successfully. If no agent is selected, validation reports that Agentic AI nodes require an agent to be selected.

Chat

Select the chat to send the message to, or provide a chat ID from a variable. Choose one of these options:

  • Select A Chat: Pick an existing chat session.

  • From Variable: Resolve the chat from a runbook variable.

Content

Specify the content submitted to the agent as a message. Choose one of these options:

  • Enter The Content Text: Type the message content in the node.

  • From Variable: Resolve the message from a runbook variable.

  • From Parent Node: Use output from the parent node.

  • From Trigger: Use content from the runbook trigger.

Data and error outputs

The Agentic AI node exposes Data and Error outputs on the canvas. Connect the Error output when you want a dedicated branch if the agent request fails. If the Error output is not wired, failures stop the branch as with other function nodes. For shared behavior on data and error outputs, see Data and Error Outputs on Data Queries and GenAI.

Runbook compatibility

Refer to Runbook Node Compatibility Matrix for which runbookClosed An automated workflow that executes a series of steps or tasks in response to a triggered event, such as the detection of anomalous behavior generating an incident, a lifecycle event, or a manually executed runbook. types support this node in your environment.