Brazil / backend product systems / PT-BR native / English-first portfolio

Open to software engineering roles

Writing

Applied AI needs budget edges

The interesting engineering work around AI is often cost control, validation, and fallback behavior.

2026-03-131 min readTheme: AI Guardrails

The anti-pattern

It is easy to wire an LLM call into a feature and call the project "AI-powered". It is much harder, and more useful, to specify when the feature should run, what it is allowed to cost, and how the product behaves when the model fails.

What I prefer shipping

In the projects I keep in the portfolio, AI is constrained:

  • by usage budgets,
  • by narrow workflow boundaries,
  • by explicit environment requirements,
  • and by docs that describe the failure modes.

Why this matters

An AI feature that quietly burns money or creates silent bad output is not a product advantage. It is a hidden reliability problem.

The portfolio signal

When I document AI features now, I try to show the guardrails around them. That is usually a stronger signal of engineering judgment than the prompt itself.