It Sucks Being a Manager

It Sucks Being a Manager

Michael Aguilar

I’ve written quite a bit about the overall process of AI-assisted development. Not the “write code” part of it - if anything, that’s the easy part. There’s a process to writing a project which can be maintained, with bug fixes and new features.

What’s a little tough right now is constantly being in the position of being a manager, stakeholder, business, and end-user. I’ve understood it in an abstract, and tend to be careful about considering them.

It’s so very visceral now.

Which AI Model Should I Use For Coding?

Which AI Model Should I Use For Coding?

Michael Aguilar

Most of the big players (Anthropic, Google, et. al) provide all-in-one solutions for writing code. If that’s what you’re doing, that’s fine, but you may be missing out.

For one thing, they can be pretty expensive (unless your company is paying for it). Anthropic’s best - Opus - can get really expensive, really fast. Admittedly, it still costs less than paying for an overseas team, but if it’s coming out of your wallet you’re bound to notice.

Considering how quickly everything is moving, I’m sure this post will age like milk.

On this page...
Advanced AI Code Automation

Advanced AI Code Automation

Michael Aguilar

So, you’ve got a great process down for developing your code. You’ve got great documentation, 100% test coverage, good git branching and tagging, and all the other detailed steps for generating code.

It sure is a lot of typing, though, isn’t it? Very repititious. Obviously, you should automate those steps! You’re only a little bit away from typing in “Write me an app that does X,Y, and Z!” and then taking a nap while it does the work!

Not so fast…

On this page...
"AI is a bubble!" Yea, So What?

"AI is a bubble!" Yea, So What?

Michael Aguilar

“AI is just a bubble!” Yep, sure is. So what? That’s no reason to ignore it, or to brush it off as a fad. While nobody can be 100% sure exactly how it will make the world look in five years, you can be sure the world will look different.

Calling something a “bubble” is often a way to dismiss it. But history shows that even when a bubble pops, the underlying technology doesn’t just go away. It sticks around and changes everything.

On this page...
The system and user prompts

The system and user prompts

Michael Aguilar

Ever wonder why AI sometimes acts like your chatty friend and other times like a stiff librarian? The difference often comes down to two invisible ingredients: the system prompt and your user prompt. Let’s peel back the curtain.

On this page...
Reliably Building AI Systems

Reliably Building AI Systems

Michael Aguilar

I recently built a production-ready application entirely with AI assistance, 100% written by the AI - not as a proof-of-concept, but as a functional tool designed to solve complex workflow problems.

It wasn’t magic, it was work.

Update: The application code is now over 5,600 lines of code, plus 16,000 lines of code in 883 tests giving 100% coverage including branches.

AI development: the good and bad

AI development: the good and bad

Michael Aguilar

There is a lot of discussion about using AI for development. Much of it is over-stated hype, either for or against.

“AI only turns out garbage” is what some people will tell you.

“AI will replace developers” is what others will say.

Like most things, the truth is somewhere in-between.

Summary

AI-assisted development can help create code faster, but pitfalls like amplified design flaws and cascading errors demand careful handling

This article cuts through the hype by showing how unchecked AI use mirrors real-world failures like Knight Capital’s $500M loss (caused by human process gaps, not technology).

Even skilled developers like “Alice, Bob, and Charlie” introduce subtle mistakes when inheriting code under time pressure, and AI accelerates these risks by acting like a new developer every time you hit “enter” - forgetting context, skipping safeguards, and magnifying poor documentation or rushed decisions.

It is important that you need to enforce defensive practices (like file operation safeguards and explicit error checks) while juggling roles as architect, reviewer, and quality gatekeeper to prevent small oversights from exploding at machine speed.

On this page...