Oracle Cloud Infrastructure Documentation

Creating an Agent in Generative AI Agents

Before you start, ensure that you have permission to manage the service.

  1. On the Agents list page, click Create agent.
    If you need help finding the list page, see Listing Agents
  2. Enter the following values:
    • Name: A name that starts with a letter or underscore, followed by letters, numbers, hyphens, or underscores. The length can be from 1 to 255 characters.
    • Compartment: Select the compartment that you want to store the agent in.
    • Description: An optional description
  3. Welcome message: Enter a message that greets the user when they start the chat with the agent.
    If you leave this field blank, the agent starts the conversation with the default welcome message displayed as a hint text.
  4. Add knowledge bases

    Either select a knowledge base from the listed knowledge bases or create one. If you need help creating a knowledge base, see Creating a Knowledge Base in Generative AI Agents.

    Note

    You can add only one knowledge base to an agent. The agent uses the ingested data from this knowledge base.
  5. (Optional) Instructions for RAG generation: Add an instruction in natural language for the agent's responses. For example, ask the agent to answer prompts in a certain way.
  6. (Optional) Check the box to create an endpoint for this agent. You can also create an endpoint for this agent later.
  7. (Optional) Click Show advanced options and add one or more tags to the agent. If you have permissions to create a resource, then you have permission to update its tags. If you need help, see Tags and Tag Namespace Concepts.
  8. Click Create.
  • If you created an endpoint for this agent, after the agent is active, go to the agent's detail page and click Launch chat to chat with this agent.
  • If you skipped creating an endpoint for this agent, when you're ready to use the agent, create an endpoint for this agent.