Pular para o conteúdo principal
Blog

Engineering, AI and software delivery

What we have learned applying artificial intelligence in real development teams, with the sources on the table.

Agile & delivery

AI in development: what the data actually shows

One study measured 55.8% faster. Another measured 19% slower. Both are right, and the difference between them is the part that matters.

Read the article
Engineering

AI code review without lowering the quality bar

People using AI assistants write less secure code and feel more confident it is secure. The gate needs to get stricter, not looser.

Read the article
Applied AI

RAG for a knowledge base: what survives production

Filling the context window can make the answer worse even with the right passage inside it. Position matters more than volume.

Read the article
Applied AI

Evals in CI: testing what is not deterministic

Equality assertions fail when the right answer can be written ten ways. Change the question the test asks and the suite becomes useful again.

Read the article
Applied AI

AI agents in delivery: where they pay off and where they do not

If you can draw the flowchart in advance, it is a workflow. Agents only when the path depends on what gets discovered along the way.

Read the article
Agile & delivery

Sprint planning and estimation in the age of AI

The average may improve, but the range gets so wide the number stops being useful for a commitment. Task type starts mattering more than size.

Read the article
Engineering

The new technical debt: code you did not write

The old debt had someone who knew why they took the shortcut. The new one grows silently, and you discover it during an incident.

Read the article
Engineering

AI-generated tests: coverage is not confidence

Coverage answers whether the line ran, not whether anyone checked the result. The right question is whether any test fails when you break the behaviour.

Read the article
Architecture & data

From prototype to production: an LLMOps pipeline

If the prompt lives outside version control, you cannot reproduce an incident. And cost per interaction is a requirement, not a month-end report.

Read the article
Architecture & data

Observability for AI features: latency, cost and quality

There is no counter for a "good answer". Quality is observed by approximation, and a dashboard without that axis gives a sense of control the system does not have.

Read the article
Engineering

Modernising legacy systems with AI as an archaeologist

That odd condition in the shipping calculation handles a real case nobody documented. Finding that out is the dominant cost of the project.

Read the article
Applied AI

A prompt is code: version it, review it, test it

An instruction is probabilistic guidance. Code is a guarantee. Confusing the two is the most expensive mistake in an LLM application.

Read the article
Architecture & data

There is no AI without data readiness

Data problems are barely visible early and compound later. Fixing at the source looks like waste and is the only thing that prevents the large rework.

Read the article
Governance

AI governance in Brazil: LGPD, Bill 2338 and the AI Act

A reviewer who approves forty cases an hour and never rejects anything is not a control, it is a stamp. A human in the loop needs time, information and authority.

Read the article
Governance

LLM application security: injection and tool abuse

The question is not where user input comes in, it is what the model can do if it believes the wrong thing. The answer is the size of the possible damage.

Read the article