The Morning Dev

Only the news worth knowing

‹
 

Watch · Python and software design

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

Chapters

  1. 0:00Intro
  2. 1:381. Outdated Patterns
  3. 3:212. Making up Missing Requirements
  4. 5:463. Changing Unrelated Things
  5. 6:424. Generating Too Much at Once
  6. 8:165. Poor Design Decisions
  7. 10:446. Code That Looks Right but Fails
  8. 11:477. Confusing Completion With
  9. 13:37Final Thoughts
Show the full video 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 Outdated Patterns 3:21 2.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