Tutorial: Build and Run Your First AI Agent

This tutorial walks you through creating a very simple AI agent with one integration as an agentic AI tool. We'll also run the AI agent with different inputs and monitor the runs.

Background

We'll create a simple AI agent for expense reimbursement. Any expense that is less than $50 USD can be automatically approved. Any expense above $50 USD is rejected.

There's one tool in this AI agent:

• Auto Approve Expense Report

What do You Need?

• Access to Oracle Integration. If you're not yet using Oracle Integration, get a free trial of Oracle Integration.
• Connection information for the Large Language Model (LLM) to which you'll be connecting. You'll need:
  • Base URL for the LLM. Example: https://api.openai.com
  • Model to use. Example: gpt-40-mini
  • API Key for the LLM

What Do I Learn from this Tutorial?

This tutorial walks you through performing the following tasks:

• Creating a project for your AI agent.
• Creating a simple tool to automatically approve an expense report.
• Creating an AI agent that analyzes the input and uses the tool to approve the expense report.
• Running the AI agent.
• Monitoring the AI agent run.

Next Step: Workflow to Build an AI Agent