Maria Gorinova: Feedback Loops That Fix Your Codebase

Maria Gorinova (0:00)

We noticed that agents tend to become crazy with comments. The more you use the factory, the more time it passes, the longer the comments become. You need to shift your mindset to thinking of a software factory as something that your code, context and data is part of.

It is not a separate thing, it's not a separate entity, it's not some sort of like magic black box that does stuff for you that you can get angry at when it doesn't work. No, your code, your context, your data is also part of that factory.

Simon Maple (0:37)

The AI Native Dev is a podcast for developers and engineering leads at the cutting edge of AI and agentic coding. Join your hosts, Guy Podjarny and me, Simon Maple, every week as we chat with the most exciting voices in AI and tackle the biggest questions facing developers today. This is the AI Native Dev.

Yesterday, you were writing code. Today, you're prompting agents. Tomorrow, you'll be running a software factory. Agentic coding is moving fast enough to give anyone whiplash. This June, AI DevCon London sold out. Hundreds of developers, engineering leads and VPs packed in to hear speakers from Anthropic, OpenAI, Netlify and GitHub cut through the hype and get to what actually works. This November, we're bringing it back to New York. Bigger, bolder and full of people actually building the agentic future. Three days of real talks, real tools, real answers, whether you're directing the agents, building the loops themselves, leading the teams or setting the strategy. As a podcast listener, you can get 15 percent off your ticket using promo code pod15.

We have so much planned and we can't wait to have you join us in New York.

Hello, and welcome to another episode of The AI Native Dev. Today, we're going to be talking about all things agents, harnesses, and specifically loops, and in particular, feedback loops. We're going to talk about what they are, how you can create them, and how you can actually benefit from feedback loops in your organizations. Joining me today is Maria Gorinova, who is actually a repeat guest, so welcome back, Maria. How are you?

Maria Gorinova (2:20)

Thank you, Simon. Good to be back.

Simon Maple (2:23)

Last time we spoke, you talked to us about abstraction adherence, which is how agents use the right libraries, which is super interesting, but things have moved on, oh my gosh, so much more.

Maria Gorinova (2:35)

So much.

Simon Maple (2:36)

It was in this very office that I heard you speak about all things, loops, feedback loops, and software factories. In fact, one of the opening questions that you asked the entire group was, what is a software factory? And I think it means different things to different people.

I'd love to hear from you. What does it mean to you? And maybe even, how did it differ from person to person?

Maria Gorinova (3:03)

The takes were very different from each other. The responses for sure, everybody had a different concept, everybody had a different angle at which they were looking at it. Some were thinking only about automation. Other were thinking about particular designs, about particular architecture.

To me, I think the best way to describe what a software factory is, kind of like go through history really of how agents have changed in the past two or so years, or less than that.

Simon Maple (3:36)

I was going to say two years is a long time in the world of AI.

Maria Gorinova (3:38)

No, it's not two years, is it? I don't know. It feels like it's been decades, right? But actually, it's been such a short time. I think Software Factory is something we have been building towards in those many decades.

To me, a Software Factory is something where we have repeatable workflows, we have shared execution environment, and we have feedback loops. Feedback loops are ways for the factory to maintain itself, to improve itself, to make sure it's operational and it doesn't degrade into quality. Because once we go into this world of everything is done by agent, we are supervising the tasks that go into the agent sometimes, but we don't really supervise the code. We don't really go into the details of writing code or even reviewing code at times. Things deteriorate very quickly.

Simon Maple (4:43)

It's interesting you didn't mention ticket to PR. So someone raises an issue, a PR is created. But that's like a use case of the factory rather than what the factory is, I suppose.

Maria Gorinova (4:53)

Yeah. I think that is one single workflow, one single automated workflow in a factory, which happens to be, yeah, I want to write a linear issue or I want to write a Jira ticket or something of the sort, and I want this to be then implemented, then the PR to be opened and even merged automatically.