AWS Veteran: How Real Engineering Teams Run Agents

**SPEAKER_1** (0:00)
This episode is brought to you by Accenture. When you're advertising operations fall out of sync, everything else follows. Spotify and Accenture are working together to reinvent the rhythm of ad sales. Using automation, analytics, and smarter workflows to simplify campaign delivery and access better data across the business. The result? Less time spent on operations, more time connecting brands with the moments and fandoms that matter most. Learn more at accenture.com/spotify.

**SPEAKER_2** (0:31)
When you need to build up your team to handle the growing chaos at work, use Indeed Sponsored Jobs. It gives your job post the boost it needs to be seen, and helps reach people with the right skills, certifications, and more. Spend less time searching and more time actually interviewing candidates who check all your boxes. Listeners of this show will get a $75 sponsored job credit at indeed.com/podcast. That's indeed.com/podcast. Terms and conditions apply. Need a hiring hero? This is a job for Indeed Sponsored Jobs.

**Heitor Lessa** (1:00)
This cost me almost 200 million tokens to refactor, and I'm like, oh, I need to stop using Opus. This doesn't work.

**Patrick Akil** (1:06)
This is Heitor Lessa, a true AWS veteran who's trained over 8,000 architects, and he shares his blueprint for software engineering with agents today.

**Heitor Lessa** (1:14)
When leadership start questioning, and do I need an engineer plus 5,000 a month just for them to do their work, that math does not add up. Even if they forge an evidence, they forge that they run the test, and try to copy and paste the results from the internet, which they do. How do I make sure that this doesn't happen?

**Patrick Akil** (1:30)
Agents and how engineering teams work with them. We're doing something we've never done before this episode, and by the end of it, you'll want to rebuild your own software engineering workflow. So enjoy.
The size, and specifically Dublin and the tech scene has grown quite significantly. Oh, yeah. But it must be fun as well, kind of the connections you've built up and the relationships there.

**Heitor Lessa** (1:53)
Oh, yeah. I think you typically have a company where your formative years are typically there, but then Amazon was especially that the idea of a hyper growth or the idea of all you need to do is a college or this Harvard book that you read or something that you will figure out. None of these things worked for Amazon because the growth was just like staggering. I remember going from like maybe a few hundred people to like 2,000 and 4,000 people like every year and I was like, what's going on? Where are we going to end with this? And it was like, yeah, the growth was minimum 25% year over year. And it was like, and then the head count was like, yeah, let's double, let's triple, let's quadruple. And I was like, wow.
So nothing of this would work.

**Patrick Akil** (2:37)
That's incredible. In the end, you stayed there 11 years. What are some of your biggest learnings or in which role were they?

**Heitor Lessa** (2:46)
I have too many.
I think one of the interesting things about Amazon, even though the size, AWS specifically, was humongous in terms of size, in terms of people and processes and so forth, it always felt like I started up in a way. So you could move between roles and between teams. And that's some part of the reason, I suppose, I was there for so long. Before I joined AWS, I went to a meetup of AWS, but I said, I would never join a company like Amazon, or these enterprises, just like I'm allergic to these things, I just want to get something done. Yeah, here we are.
And I remember I was complaining about the presenter, but I didn't know no one in the audience, and then it was literally two guys working for AWS, like, hey, why don't you apply? I was like, yeah, I'll never do this. Like, no, it's a bit different and so forth. Ever since I applied and I joined and so forth, I went to maybe, I think, eight different roles, if I'm not mistaken. So from support to field, custom refueled, like technical account management, solution architecture, specialist solution architecture, then helping build what we call serverless in the world, the serverless business. I was the first specialist outside the US. So then even trying to hire developer advocates and everything else, I had to learn how to do the role until we managed to hire. All these things, it doesn't feel like Amazon from the outside, but the inside was like, let's just move, let's just build these things. So in terms of learnings, the three roles, the three different roles that were marked, I think, the way I think was something called technical account manager. You typically are called when things go wrong. So think like, I'm having an outage now, we're having a big incident, or you started using AWS, you lift and shifted, and now your span just went through the roof, and you're trying, how do I optimize this span? So all these things that people don't really want to, they don't come nice to you, and like, oh, hello, I mean, here's the problem I have. And it's just like, any help now, I need to solve now. So that one was when I met companies that people didn't want to work with eventually. Those were kind of gaming companies in the early days, or startups that were seeing unprecedented growth. So you would see things like microservices in 2015 of these companies, or doing DevOps at scale, or API first teams. So this was 2015