Welcome to my learning journal

Welcome. This blog is born as my learning journal: a place where I will write down what I keep learning, with the idea that over time it becomes my personal knowledge base in the open.

I have spent over a decade building backend software, automating processes and keeping critical systems alive in production. I learned an enormous amount along the way, but almost none of it got written down. I want to fix that, and I want to do it in public, because explaining something is the best way to confirm you truly understand it.

And I cannot think of a better moment to start.

A unique moment

Generative artificial intelligence is turning upside down the way code has been written until now. That is not marketing hype. Anyone working in this field feels it every week in their own workflow.

The data backs up the feeling. As of early 2026, close to half of all new code is already generated by AI. And the next wave is already here: we have moved from assistants that autocomplete lines to agents that research, execute, iterate and verify entire tasks. Gartner estimates that 60 % of enterprise AI rollouts will include agentic capabilities by the end of 2026.

That said, healthy skepticism is worth keeping. A controlled trial by METR found that, on codebases they knew well, some experienced developers were actually slower with AI than they themselves perceived. The tool does not replace judgment: it amplifies it when it exists and exposes its absence when it does not. That is exactly why learning to use it well matters, and a good part of this blog will be about that learning.

From implementers to engineers

For years, a large part of our job was translating decisions that had already been made into code. We were, above all, implementers: people who turned specifications into syntax.

When the machine does the typing, the value moves up a level. Our work starts to look like what engineering was always supposed to be: truly understanding the problem, designing the architecture, weighing the tradeoffs, deciding what to build and why, verifying that what was built actually works, and optimizing what really matters. We go from typing to supervising and orchestrating, from executing tasks to making higher level decisions.

There is another effect that matters just as much: we get time back. Time for the tasks that are also engineering and that always got postponed: measuring, documenting, simplifying, automating, teaching others. AI is not taking the craft away from us. It is giving us back the part of the craft that deadlines had stolen.

Beyond software

Software is only the first sector to be transformed, because it is the only one that transforms itself. But the wave does not stop there.

In healthcare, 63 % of professionals are already actively using AI, mostly to reduce administrative burden and speed up diagnosis. In manufacturing, the combination of sensors and computer vision is cutting machine downtime and taking quality control to levels human inspection cannot reach. In legal services, specialized models draft and analyze contracts that used to consume hours of junior work.

The pattern repeats everywhere: repetitive tasks fall first, then entire workflows get redesigned. Whoever understands that transition early will play with an advantage, whatever the sector.

What you will find here

I will write about what I work on and what I learn, with AI as the thread running through almost everything:

1. Engineering in the age of agents: how I design, supervise and verify what the models build, instead of typing it myself line by line.
2. Backend and production systems: performance, reliability, and the boring decisions that prevent incidents in the middle of the night, now with AI woven into the workflow.
3. Process automation: what is worth automating, what is not, and how to tell the difference, both with models and without them.
4. Prompting, agents and tooling: how to iterate well, how to judge what a model gives back, and the traps you only discover by using them for real.

No fixed schedule and no filler: I will publish when I have something genuinely worth sharing. If any of this resonates with you, welcome aboard. See you soon.