Configuring an agent is one of the foundational steps in building effective Agentflows. In this short how-to video, you'll learn how to configure a single Agent Action and understand the key components that influence how an agent behaves, accesses information, and returns results.
Whether you're building your first AI-powered workflow or refining an existing Agentflow, this overview will help you understand the core configuration options available.
What You'll Learn
This video provides a high-level walkthrough of:
- Adding an Agent Action to an Agentflow.
- Understanding the four key configuration areas:
- Model
- Tools
- Knowledge
- Output
- Selecting and configuring an AI model and connection.
- Adjusting model settings such as:
- Reasoning effort
- Temperature
- Defining the agent's:
- Role and rules
- Work request
- Adding and using tools to enable agent actions.
- Connecting agents to knowledge sources and document stores.
- Understanding shared context and external vector embeddings.
- Configuring user message and structured outputs.
- Storing agent responses in variables for use elsewhere in your process.
Watch the Video