AI Coding Programming
/

Google Issues First Official AI Coding Guidelines to All Software Engineers

Company sends comprehensive guidance as AI generates over 30% of its code.

Google has sent official AI coding guidelines to all its software engineers, marking the company’s most formal approach to artificial intelligence adoption in development work.

What Google Told Its Engineers

On Monday, Google emailed comprehensive recommendations to all software engineers about using AI tools for coding. The guidance covers:

  • Best practices for AI-assisted coding
  • Understanding AI capabilities and limitations
  • How to build AI-based systems
  • Ways for managers to integrate AI development in teams

The document was created by Google engineers based on what has worked well at the company so far.

AI Now Generates 30% of Google’s Code

Google CEO Sundar Pichai revealed that AI now generates over 30% of code at Google. This number has grown by more than 5% in just six months.

The process works with AI creating code and human engineers reviewing it before approval. Google emphasizes that engineers must maintain strict standards for code review, security, and maintenance.

Productivity Gains Drive the Push

Google reports that AI usage has increased engineering velocity by an estimated 10%. Engineering velocity measures how much software work gets completed in a specific time period.

The company expects all engineers to use AI to boost their productivity, hoping this leads to faster development and more rapid iteration on projects.

Beyond Just Coding

The guidance also encourages employees to explore AI uses beyond writing code. Google wants engineers to understand how AI can help with other aspects of their work.

Company’s Broader AI Strategy

This internal guidance follows Google’s external AI tool releases, including:

  • Gemini Code Assist
  • Gemini CLI
  • Gemini integration in Android Studio

Official Company Statement

Google confirmed the guidance in a statement: “Our engineering teams are already regularly using our AI tools for coding, fixing bugs, and much more. These recommendations and best practices, developed by a group of software engineers at Google, are designed to help all SWEs across the company get the most out of AI in their day-to-day work.”

The move shows Google’s commitment to making AI a standard part of software development across the entire company.

Sazid Kabir

I've loved music and writing all my life. That's why I started this blog. In my spare time, I make music and run this blog for fellow music fans.