To begin creating an agent, click on the Create Agent button and follow the guided setup flow.
.png?sv=2026-02-06&spr=https&st=2026-09-10T10%3A42%3A39Z&se=2026-09-10T10%3A53%3A39Z&sr=c&sp=r&sig=tCJZF4dqUqzBbnR%2FLgPw3yYDPwzQkotWFMTX%2FEg07ts%3D)
The Create an Agent window opens. The left‑hand panel displays guided steps to help you move through the setup process, while the right‑hand panel displays the Agent Basic Setup fields that you must complete.
Agents are configured through a guided setup process that defines the agent's purpose, knowledge, capabilities, operational controls, and deployment settings. Each stage focuses on a specific aspect of the agent configuration.
Basic Setup
Configure the agent's core identity and behavior by defining its name, goal, context, and the Large Language Model (LLM) that powers its reasoning and decision-making. This information establishes the foundation for how the agent operates.
Knowledge Base
Provide the information the agent can reference during execution. Knowledge sources can include documents, business information, reference materials, FAQs, and other supporting content that helps the agent generate more accurate and contextually relevant responses.
Tools
Define the actions and external capabilities available to the agent. You can configure Xponent Graphs, API-based integrations, and built-in tools that enable the agent to retrieve information, invoke workflows, and interact with external systems.
Guardrails
Configure policies, restrictions, and safety controls that govern the agent's behavior. Guardrails help ensure the agent operates within defined boundaries and complies with business, security, and operational requirements.
Confirmation
Review the completed configuration, submit the agent for creation, and monitor the build process. This stage provides deployment details, the generated Agent ID, and status information that confirms when the agent is ready for use.