In software engineering, thinking is the expensive part. It always has been. Writing code? That’s the cheap bit. Typing fast is great, but don’t let that speed fool you. Here’s something to remember: code is read many times but written only once (ref: Robert C. Martin). The real cost comes later, when you have to fix bad design. That’s when you pay, and you pay a lot. The real work is in the judgment calls, the choices, and the structure you set up at the start. That’s what makes an engineer valuable.
Now, let’s talk about AI. LLMs are like a megaphone for your habits. If you know what you want, you can try out ideas at lightning speed. But if you don’t, you end up with a “Big Ball of Mud a.k.a. Spaghetti Code”. It’s so easy to make a mess when the machine never gets tired. You can’t rely on the model to deliver high quality software. You have to give it context. You have to explain what matters, what the rules are, what the tests should check, and why you made the choices you did. That’s context engineering, and it’s a real job. It’s not just a prompt you paste in and forget. It’s the glue that keeps your intent alive, even when the code changes a hundred times.
So what do you do? You do what good engineers have always done. You plan. You write things down. You test as you go. You check your work, and you help others learn how to do the same. You take responsibility for what you build. If you build it, you run it. That’s the deal. Don’t just count lines of code or how fast someone types. Look at what lasts, what works, and what makes life easier for the next person who reads your code. If you get this right, AI will make you faster and better. If you get it wrong, AI will just help you make a bigger mess, faster.
If this resonates with you and you want to go deeper, check out the idea of context engineering. It’s all about managing what information you give to your AI tools, and when. The quality of your results depends on what you feed the model. Good context means better output, less slop, and fewer headaches for everyone. There’s an effective way and a useless way to use AI’s limited context window, and knowing the difference makes all the difference. For a practical take on this, read my article “Context Engineering: Mastering AI Tools”.
see: https://www.tqdev.com/2025-context-engineering-mastering-ai-tools