Pedro Sousa
Português

Blog

Reflections on engineering, AI and product.

20 articles

Featured

How I work with AI: I don't ask for code, I configure the environment the AI works in

I believe the real gain with AI didn't come from better prompts, it came from changing the question. Instead of asking for code, I engineer the environment, the harness, where the agent works within my standards.

AIClaudeMobile DevelopmentiOSDeveloper ProductivitySoftware ArchitectureAI AgentsMCP
Jun 24, 2026
Read article ›

More articles

Oct 18, 2026

The @State you dumped in the View isn't a SwiftUI problem. It's a problem of where the decision lives.

Most architecture problems in SwiftUI don't start with the framework. They start when you decide where state lives without understanding what that decision is going to cost you six months from now. This isn't MVVM theory. It's what happens when the app grows and the @State was never built to grow with it.

Read article ›
Oct 11, 2026

The context you send to the agent is the product. Not the prompt.

Most teams treat context engineering as an implementation detail. In practice, it's the most important architectural decision in any LLM-based system. When it breaks in production, the model is not the problem.

Read article ›
Oct 04, 2026

An agent that decides too much is just as dangerous as one that decides too little

Most problems with AI agents in production don't come from hallucination. They come from bad boundary design: the agent takes on responsibilities it shouldn't have, or gets stuck waiting for confirmation on trivial things. This article is about how I learned the difference in practice.

Read article ›
Sep 27, 2026

You broke into the international market. And kept thinking local.

Working internationally isn't really about time zones or language. The most common problem is carrying a career mental model that was built for a completely different market. That costs you more than any technical gap ever will.

Read article ›
Sep 20, 2026

You chose Kotlin Multiplatform. And your ViewModel became a blind knot between two platforms.

Kotlin Multiplatform promises to share logic. What nobody warns you about is that sharing a ViewModel between Android and iOS changes what the ViewModel needs to be, and that breaks both sides. A decision I've seen cost weeks of refactoring.

Read article ›
Sep 13, 2026

The interface you hid behind a protocol didn't disappear. It just became harder to find.

Extracting a protocol doesn't solve coupling. In most cases, it just moves the dependency somewhere the compiler stops complaining about. The problem is still there, it just became invisible.

Read article ›
Aug 23, 2026

The agent didn't make a mistake. It answered exactly what you asked.

Most problems with AI agents in production aren't hallucination or model limitations. It's that the engineer doesn't realize they're asking the wrong question. The model delivers what it received. The problem happens before the call.

Read article ›
Aug 16, 2026

You didn't refactor the code. You just moved the problem somewhere else.

Refactoring is not reorganizing code. It's changing internal behavior without changing external behavior, and most refactors that happen in real projects don't do that. They just relocate where the problem lives.

Read article ›
Aug 09, 2026

The model didn't forget. You never explained it properly.

Most problems with LLMs in production aren't model failures. They're failures by whoever built the system around it. Context engineering isn't an optional step: it's the only part that actually matters.

Read article ›
Aug 02, 2026

What nobody tells you about working internationally: the problem isn't your English

Most Brazilian engineers who try to break into international careers get stuck in the wrong place. Language isn't the bottleneck. The way you communicate technical decisions is.

Read article ›
Jul 26, 2026

Kotlin Multiplatform is not Flutter. And that confusion is costing entire architectures.

Most teams adopt Kotlin Multiplatform with the same mindset they'd use for Flutter, and that's when things start to fall apart. Sharing logic across platforms is different from sharing a product. That distinction rarely shows up early enough.

Read article ›
Jul 19, 2026

RAG didn't fail because of search. It failed because of the context you didn't give the model.

Most RAG problems in production aren't about document retrieval. They're about poorly constructed context passed to the model. This article explains why the pipeline works in testing and breaks in the real world, and what I would change today.

Read article ›
Jul 12, 2026

Flutter solves the wrong problem when you already have a working Kotlin app

The decision to go cross-platform is almost always made before anyone understands what problem is actually being solved. I've worked on both sides of that decision, and the mistake I kept seeing wasn't technical. It was a misdiagnosis.

Read article ›
Jul 05, 2026

The abstraction you created to simplify things will be your next maintenance problem

Every abstraction is born from good intentions. The problem is that it ages without warning, and by the time you notice, it's already spread across ten places you no longer control. That's the cost nobody puts in the PR.

Read article ›
Jun 28, 2026

The agent that worked in testing and broke in production

Building an AI agent that works in a demo is straightforward. The problem shows up when real context arrives: noisy data, long sessions, ambiguous states. Most teams find that out after deploy.

Read article ›
Jun 21, 2026

Working abroad doesn't make you senior. Context does.

I went to work at a software factory in France thinking the geographical leap would change my technical trajectory. It did, but not in the way I expected. What actually happened was slower, more uncomfortable, and more useful than anything I could have planned for.

Read article ›
Jun 13, 2026

SwiftUI Preview as an Architecture Sensor

When a Preview starts demanding acrobatics just to work, the problem is rarely the Preview. The problem is the architecture. I learned that the hard way, trying to fix the symptom instead of the cause.

Read article ›
Jun 11, 2026

The pattern you won't refactor because it's working

Bad technical decisions rarely blow up. They just stay. This article is about the kind of code that survives not because it's good, but because it works just enough to never become a priority.

Read article ›
Jun 07, 2026

The module that knows too much is not a module. It's a monolith with extra files.

Modularizing a project without modularizing the thinking creates an illusion of isolation. The practical result is a monolith distributed across folders, with invisible coupling and increasingly slow builds.

Read article ›