Test Your Agent

Make sure your agent is behaving as expected.

Overview

In this article, we cover testing your AI agent.

This article is part of a series covering setting up and deploying AI agents. See the other parts in the series:

  1. Create an AI Agent
  2. Write a Behavior Description (Prompt)
  3. Create Actions and Tools
  4. Add Your Knowledge Center
  5. Add Input Parameters
  6. Check Your Agent
  7. Test Your Agent - this article
  8. Integrate into a Flow
  9. Use Multiple Agents

Testing Your Agent

❗️

Important:

Testing new agents is mandatory!

AI agents are like people. They can give different answers to the same questions based on the instructions and information they're provided. The only way to know is to test.

You wouldn't hire an employee without an interview, so don't release a new agent without testing.

When you're done building your AI agent, it's important to run some tests and make sure it's answering questions and taking actions the way you expect.

This is also the time to think up and try out any edge cases you can think of, to confirm whether your agent responds appropriately.

Testing can be done in two ways, and we recommend you use both options every time you build a new agent:

  1. From the AI Agent tester:

  2. From the flow tester:

🚧

Note:

Tests from the AI Agent tester and tests from the flow tester are likely to produce different results.

This is because tests from the AI Agent tester do not have any conversation history context, while tests from the flow tester do.