I Let AI Write My Code. Then I Read It...

<p><strong>Want to get into the top 10% of your engineering team by leveraging agentic engineering workflows? I&#39;m planning a 2 day workshop here: </strong><a href="https://form.typeform.com/to/EDuBEz4U">https://form.typeform.com/to/EDuBEz4U</a></p><p><br></p><p>I shipped a feature with AI in record time.</p><p>Then I actually read the code.</p><p>60+ files. Weird abstractions. Tests that technically passed but proved almost nothing. Components rebuilt from scratch for no good reason. What looked like a finished feature was probably 70–80% of the way there.</p><p>And the worst part? This wasn’t my first time doing this.</p><p>I’ve also sat in a code review as a senior engineer and realized I couldn’t properly explain code that “I” had just written.</p><p>I use Claude and Codex constantly. I’m not going back to hand-writing everything. But after using AI to build software at startups, inside my own business, and on large production systems, I think we’re learning the wrong lesson from how fast these tools can code.</p><p>The question isn’t whether AI can write the code.</p><p>It’s how much you need to understand before you’re willing to ship it.</p>