Squashing Bugs with AI Agents
Published by O'Reilly Media, Inc.
Fast fixes with Claude Code and friends
Course Outcomes:
- Use a tried-and-true bug fixing process with the help of an AI agent
- Learn how to avoid being bitten by confabulated AI bug fixes
- Quickly reproduce user-reported bugs
Your users have identified a bug in your application. The time it will take to fix it could derail your day and eat into your week, but an AI agent could help save you both time and energy. In this hands-on course, Python expert Trey Hunner shows you how to use Claude Code and similar AI agents to reproduce bugs, fix them, and future-proof your code against regressions.
What you’ll learn and how you can apply it
- How to use Claude Code and similar AI agents to help identify, reproduce, and fix bugs in your codebase more efficiently.
- Best practices for writing automated tests to reproduce user-reported bugs and using red-green testing approaches to resolve them.
- Techniques for validating bug fixes through strategies like code coverage analysis, AI-assisted code review, and Socratic questioning to identify potential regressions.
- Hands-on experience setting up Claude Code and using it practically to streamline debugging workflows and future-proof your application.
This live event is for you because...
- You’re a programmer.
- You have access to Claude Code or another LLM-based AI agent.
- You want to use an AI agent to quickly fix bugs.
Prerequisites
- A computer with Python 3.9+ and Node.js 18+ installed
- A Claude subscription (Pro or Max) or a Claude API account with valid billing information on file (necessary for participation in exercises)
- Git 2.23+ (recommended)
Recommended follow-up:
- Explore Python Essentials (on-demand course)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Installation and setup (25 minutes) Hands-on exercise: Install and set up Claude Code
Reproducing bugs (25 minutes)
- Presentation: Reproducing a user-reported bug
- Hands-on exercise: Write a test for a bug
- Q&A
Fixing bugs (35 minutes)
- Presentation: Fixing a bug with red-green testing
- Hands-on exercise: Fix a bug
- Break
Verifying correctness (35 minutes)
- Presentation: Coverage, code review, and Socratic questioning
- Hands-on exercise: Fix a buggy bug fix
- Group discussion: Pitfalls to watch out for
- Q&A
Your Instructor
Trey Hunner
Trey Hunner helps Python programmers level up their skills through corporate training and through Python Morsels, a Python skill-building service for individuals and small teams. Trey also sends out a new Python tip every week through his email newsletter at pym.dev/newsletter.