Pull Requests blog posts

Split-screen image: left side shows a figure standing alone in a sparse room facing a single sticky note on a bare wall; right side shows the same figure actively working at a dense investigation board covered in documents, strings, and notes.

We Ran the Same Experiment Twice. Different Feature, Different Models, Same Winner.

Discover why budget LLMs equipped with full code context consistently outperform flagship coding agents like Claude Code and Gemini CLI in PR generation.

Three stacks of printed pull request descriptions on a dark desk, labeled PR 1, PR 2, and PR 3 from left to right. PR 1 is the thinnest stack showing a sparse git diffstat and oneline commit log. PR 2 is a medium stack with a structured markdown summary and What's Changed section. PR 3 is the thickest stack showing Key Design Decisions and a numbered Test Plan, with a gold trophy resting on the top-right corner — indicating it ranked first in a blind evaluation by Gemini.

AI Development Workflows

We Had Gemini Blind-Judge Three Claude-Generated Pull Requests. Here's the Template It Built.

We had Gemini blind-judge three Claude-generated pull requests. Here is the exact AI pull request template it built, and why rich code context is essential.