Skip to main content
AmigoFish

7 Things AI Coding Agents Get Wrong (Because You Let Them)

From ArjanCodes · · 13 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.

If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.

Watch on YouTube

Not rated yet

Description

🧱 Build software that lasts. Join the Software Design Mastery program → https://arjan.codes/mastery.

AI coding agents can write code incredibly fast, but they can also make some surprisingly bad decisions.

In this video, I share 7 common mistakes AI coding agents make and practical ways to avoid them. From unclear requirements and unnecessary changes to poor software design and unreliable tests, we'll look at how to guide AI agents more effectively, review their work, and build software that stays maintainable.

🔥 GitHub Repository: https://git.arjan.codes/2026/aicoding.

💬 Join my Discord server: https://discord.arjan.codes.

⌨️ Keyboard I’m using: https://amzn.to/49YM97v.

🔖 Chapters: 0:00 Intro 1:38 1. Outdated Patterns 3:21 2. Making up Missing Requirements 5:46 3. Changing Unrelated Things 6:42 4. Generating Too Much at Once 8:16 5. Poor Design Decisions 10:44 6. Code That Looks Right but Fails 11:47 7. Confusing Completion With 13:37 Final Thoughts

#arjancodes #softwaredesign #python

Back to ArjanCodes · Report a problem