Amazon Revises Engineering Guidelines for AI Written Code

Nov 3, 2026
Amazon revised its software engineering guidelines to focus on outcomes as AI agents write most code for many of its developers.

Amazon revised its software engineering role guidelines, extending its earlier warning against optimizing work around AI usage metrics, according to GeekWire. The guidelines emphasize measuring engineers and teams by outcomes rather than token use or lines of code.

Amazon Web Services vice president Marc Brooker said AI agents now write almost all the code that most Amazon developers previously wrote by hand. Usage data can still inform evaluations, but the company advises managers to apply those metrics with care and judgment.

Brooker also leads Velocity Labs, a team of about 35 people formed within Amazon Web Services in April. The group builds rapid AI prototypes and recently moved an open source AI model from concept to public release in less than a week.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Guide
AI app builders

AI app builders

Tools that turn a description into a working web or mobile app, and the platforms companies use to build internal tools with AI

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.