From the course: AI Evaluations: Foundations and Practical Examples
Unlock this course with a free trial
Join today to access over 25,200 courses taught by industry experts.
Hands-on lab: Vibe code auto evaluations using Cursor
From the course: AI Evaluations: Foundations and Practical Examples
Hands-on lab: Vibe code auto evaluations using Cursor
- [Presenter] In last module, we saw how can you set up manual evaluations, but you needed a lot of experts to do those evaluation and that's a lot of time. And we thought we can actually use AI to evaluate AI and that's this module is about. But before we go there, I thought I will quickly show you how can you use Vibe Code to create an AI agent, and then we can use that agent for our evaluation exercise. So I'm using Cursor. This is the AI code editor. It allows you to use an AI agent to write code. How you use it is you go to cursor.com, you click "download," it gives you a file, and all you have to do is you take that file and you put that file in your applications. So let me just do it for you. And you just scroll it, put it here, and that's cursor for you. So that's pretty much it. I already did it. So it says replace or stop, I will just stop. So that's how you install Cursor and get going. Once you have done that, you can actually click here, and say, "Cursor." By the way, I'm…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
(Locked)
Decomposing AI agents into evaluative components4m 6s
-
(Locked)
Identifying high-risk or hard-to-evaluate components5m 10s
-
(Locked)
Manual evaluation with criteria8m 14s
-
(Locked)
Defining evaluation criteria from MVP to GA4m 58s
-
(Locked)
Hands-on lab: Vibe code auto evaluations using Cursor8m 29s
-
(Locked)
Hands-on lab: Automating AI evaluation using LLM as judge9m 27s
-
(Locked)
-
-