Heads up! To view this whole video, sign in with your Courses account or enroll in your free 7-day trial. Sign In Enroll

Add Guardrails and Safety to Your AI Agent - AI Agents Day 25

Well done!

You have completed Add Guardrails and Safety to Your AI Agent - AI Agents Day 25!

Sign up for Treehouse Back to Library

AI Agent Guardrails and Safety Best Practices

13:35 with Daniel Montgomery

Learn practical ways to make an agent safer. Trim your instructions to the essentials, restrict each agent to the smallest set of tools it needs, then test the boundaries with requests your agent should refuse.

This is part of the AI Bootcamp. Click here to learn more.

Related Discussions

Have questions about this video? Start a discussion with the community and Treehouse staff.

Sign up

    Related Discussions

    Have questions about this video? Start a discussion with the community and Treehouse staff.

    Sign up

    Earlier in the program, you had your project spec that we converted into a 0:00
    specific agent spec. 0:03
    We then further iterated on that spec by creating our Agent Goal spec or Agent Goal prompt. 0:04
    Today, we're going to go over how to implement this with your agent and ensure 0:10
    your agent is listening to the boundaries and guardrails you're setting, so the 0:14
    agent only answers and responds in the ways you want and expect it to. 0:17
    And I'm I'm actually starting in the Google Doc, so you can see my agent goal 0:22
    prompt here from my agent Robbie. 0:25
    It includes all the sections you'd expect and that we discussed earlier in the program. 0:27

    You need to sign up for Treehouse in order to download course files.

    Sign up

      You need to sign up for Treehouse in order to set up Workspace

      Sign up