Project

Building a PR Review Agent

Challenging

17 completions

~ 19 hours

4.6

You will explore agent design patterns—state maintenance, tool calls, and handoffs— and gain hands-on Python practice interacting with GitHub repositories programmatically. This will equip you with the knowledge needed to design agent systems that collaborate to accomplish a shared goal.

Provided by

JetBrains Academy

About

In this project, you’ll build a multi-agent AI system that taps into GitHub’s API to pull code diffs, test outcomes, and dependency data. It then uses this information to catch obvious mistakes—lint violations, missing tests, and vulnerability flags—and produces a short, clear comment for each pull request. Finally, it posts the review back to GitHub, so reviewers can dedicate their effort to the deeper review tasks.

Graduate project

This project covers the core topics of the Introduction to AI Engineering with Python course, making it sufficiently challenging to be a proud addition to your portfolio.

At least one graduate project is required to complete the course.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:

Set up a repository to develop and test the agent.

Build an agent to prepare the needed context.

Use the retrieved contexts to generate draft comments.

Analyze the draft review, refine it, generate a final review, and post the final comment.

Wrap it all up in a GitHub Actions workflow to create review comments automatically.

Reviews

Diego Pérez Petkov

2 weeks ago

4.0

Great project. SUper interesting to see how to work and let LLM-based agents aid you with different tasks through multi-agentic workflows. Definitely one of the best projects out there!

Marcin Borkowski

2 months ago

5.0

Great project, really amazing! It shows how to orchestrate agents with high-level functions — ideal for prototyping, demonstrating how it works, and serving as a good introduction to more personalized, complex low-level architectures.

Andrei Fralou

3 months ago

4.3

Sometimes it was difficult way, but now I'm just in the beginnig!

4.6

Learners who completed this project within the Introduction to AI Engineering with Python course rated it as follows:

Usefulness

4.9

Fun

4.6

Clarity

4.4