Autoresearch: The feedback loop behind self-improving agents
SubscribeSign in
AINews: Weekday Roundups<br>Autoresearch: The feedback loop behind self-improving agents<br>Introspection co-founder Roland Gavrilescu explains autoresearch, agent “recipes,” self-improving loops, and why humans remain central to the software factory.
Richard MacManus<br>Jul 01, 2026
64
Share
Introspection’s Roland Gavrilescu at AIEWF.<br>We’ve heard a lot about loops at the AI Engineer World’s Fair this week. Another buzzword is autoresearch , which involves building an “outer loop” where agents help maintain and improve the primary system, using feedback signals, evals and human input to make progress over time.<br>At least, that was the framing of Roland Gavrilescu, co-founder and CEO of Introspection — a new company building infrastructure for deploying these self-improving systems. Before starting the company, Gavrilescu worked on agent infrastructure and cloud agents at xAI, where he met his co-founder, Julian Bright.<br>Ahead of his “Autoresearch in the Wild” session at the AI Engineer World’s Fair today, I spoke with Gavrilescu about the shift from agent harnesses to feedback loops, the role of the open-source Pi framework, and why autonomous software factories must first learn from humans.<br>From xAI to Introspection
Latent Space: How did your new company, Introspection, come about?<br>Roland Gavrilescu: Last year, I was at xAI, where I met my co-founder. We were working on agent infrastructure and cloud agents, and we felt there was a new agent form factor that needed to be explored further. xAI was not necessarily the environment where we could focus completely on that.<br>We decided to leave and ask what a company designed around this new form factor might look like. We were interested in what made companies such as Cursor and Cognition successful, and how we could turn some of those ideas into a product that others could use.<br>That became the basis for Introspection.<br>Autoresearch allows you to build loops in which agents help maintain the system itself. The challenge is designing the right signals and feedback mechanisms so agents can improve the system, make architectural decisions and move in the right direction without constantly being bottlenecked by humans.<br>The loop becomes the product
Latent Space: Your session is titled “Autoresearch in the Wild” — what will it cover?<br>Gavrilescu: We have heard a lot about what autoresearch can do for improving experiments, but we wanted to talk about what these loops look like in production.<br>We are presenting three patterns that we think form the basis of a new blueprint.<br>The first is that the loop is the product . We have moved from focusing on models, to harnesses, and now to loops. The key question is whether you can define the right feedback mechanisms so agents can take on more work without generating more slop.<br>The second pattern concerns what the loop generates and how you track it over time. We are proposing a concept called an agent recipe .<br>We moved from agent tools to agent skills. Recipes are a larger container that brings together the components needed to encode human expertise: evals, judges, signal processing and the information that feeds back into the loop.<br>The goal is to create a portable format that agents can iterate on, almost like a research laboratory, but in a provider-agnostic way.<br>The third pattern is about what we optimize for. How can the system become both better and cheaper over time?<br>Companies such as Cursor and Cognition have shown that these products can work. The next stage is making them more accessible, faster and cheaper, and gradually distilling the capabilities of frontier models into systems that you own and that are customized for your environment.<br>Agent recipes
Latent Space: Can you explain more about what an agent recipe is…<br>Gavrilescu: It’s like a description of the ingredients you need and how they evolve.<br>The idea comes partly from data recipes used in model post-training. A data recipe describes how much data from different domains should be baked into a model.<br>Agent recipes are similar. A recipe might describe how your harness works with different models, the evals you use, the judges you have created, the human expertise you have captured and the failures that led to new evals.<br>Imagine that tomorrow you suddenly gained access to the Devin codebase. The code alone would not necessarily be that helpful if you could not see how the team arrived at the current version. You would want to understand the failures, mistakes and decisions that informed it.<br>A recipe captures that process. You begin with a baseline and then record how each signal produced a new judge, embedded new human expertise or led you to introduce a different model.<br>The inner loop and the outer loop
Latent Space: Does autoresearch mean orchestrating multiple agents, or can it involve one agent repeatedly working and verifying its results?<br>Gavrilescu: You can think of the system as...