Federico, what experiences led you to build Density Lab and why did you decide to to focus on helping companies successfully implement AI instead of simply talking about it? It's a

very interesting question.

So my journey has been about first learning the craftsmanship of building software and being able to understand the in deeper level how software works, how to build elegant solutions and elegant code, right? That goes beyond what is actually needed to make it work because the issue is what happens when you want to read it again in a month, three months, or a year, and you need to make a fix or you need to make an improvement, right? So being able to have clear, elegant code allows you to understand that faster, easier, right? Because...

You know, we kind of forget, humans, we kind of forget why we wrote it that way, right? So choosing the name of the variables becomes an important thing because what you're trying to do is you're trying to represent a problem in real life or a workflow.

You're trying to build it with software, right? So I've been obsessed with that concept.

that level of detail, right? And elegant solutions is the best way that I can describe it, right? So from there, I did it for myself and then I started teaching other people how to do that properly, right? And then from there, I went towards what I realized is that there were a lot of skills that I was doing myself That I didn't realize until I explained to other people that they wouldn't do it the way that I was doing it.

And then I started getting into soft skills, communication skills, really understanding what are the requirements of what we need to build.

Where do AI agent generally create value and where do you think companies are overusing them? So we're

So when putting AI agents into an engineering org, what are some of the things that break or some of the challenges that you see?

Even though I am advocating for the use of AI, I believe that using as little AI as possible is the best approach.

So what are the best scenarios to leverage AI within an organization? So when we have business processes, right, and we want to automate them, we can use an AI agent to just automate the whole workflow, right? or we can build software, we can build code that is actually going to automate that workflow, right? So what I am advocating is to build code to solve the automation for all the deterministic workflows.

By deterministic, I mean, think of math.

Math is deterministic.

One plus one equals two, right? It's always the same result.

So when we have those type of rules or we can set up those type of rules, then we can build code.

Where do they encounter problems doing that?