How is Google using AI for internal code migrations?

TL;DR

This paper shares Google's experience with applying large language models for internal code migrations, highlighting how LLMs can significantly reduce migration time and barriers in an enterprise setting.

Contribution

It provides practical insights and lessons learned from deploying LLMs for code migration at Google, an area lacking extensive empirical research.

Findings

LLMs can significantly cut migration time.

Using LLMs lowers barriers to starting and completing migrations.

Insights are applicable to broader ML applications in software engineering.

Abstract

In recent years, there has been a tremendous interest in using generative AI, and particularly large language models (LLMs) in software engineering; indeed there are now several commercially available tools, and many large companies also have created proprietary ML-based tools for their own software engineers. While the use of ML for common tasks such as code completion is available in commodity tools, there is a growing interest in application of LLMs for more bespoke purposes. One such purpose is code migration. This article is an experience report on using LLMs for code migrations at Google. It is not a research study, in the sense that we do not carry out comparisons against other approaches or evaluate research questions/hypotheses. Rather, we share our experiences in applying LLM-based code migration in an enterprise context across a range of migration cases, in the hope that other industry practitioners will find our insights useful. Many of these learnings apply to any application of ML in software engineering. We see evidence that the use of LLMs can reduce the time needed for migrations significantly, and can reduce barriers to get started and complete migration programs.