Autoresearch isn’t just for training models (2026) - Shopify

This post introduces `pi-autoresearch`, an extension for the Pi agent harness that implements an iterative optimization loop inspired by Andrej Karpathy's Autoresearch. The extension focuses on improving a target metric (e.g., build time) by forming hypotheses, testing them, and retaining improvements that lead to faster execution or successful builds. It includes features like custom UI for iteration tracking, a focus on a specific metric, and a continuous looping mechanism. The post highlights the value of autonomous agents for tackling tedious but valuable optimization tasks that humans might deprioritize. The project was subsequently open-sourced and saw significant adoption and contributions.