news

Amazon's anti-tokenmaxxing memo says engineers should be pickier about using AI

CNBC reports on an Amazon memo, shared internally in September and made public Oct. 27, that labels token usage, AI tool adoption rates and code-change counts 'deeply flawed' gauges of a team's AI use.

Published 2026-10-27Source: CNBC
CNBC source artwork

Why it matters

Amazon is the company that scrapped an internal leaderboard in May after staff gamed it. It now has a written replacement: judge teams on long-term outcomes, and weigh token and code-generation counts with judgment alongside other data.

Tokenmaxxing read

The memo's sharpest line cuts against every adoption dashboard: work that gains nothing from today's AI tools is 'a finding, not a failing.' Naming the tasks where the tools fall short is treated as the skill itself. A leaderboard has no column for tokens declined.

Source takeaway

AWS VP Marc Brooker told CNBC the yardstick is 'feature velocity': launches and successful changes in production. Amazon says it has set no caps on employee token use, and Brooker wants room to experiment because it isn't always clear which problems matter.

Topic links

Related projects

Tools that match this angle

#2Direct
Observability

Langfuse

langfuse/langfuse

Open-source LLM engineering platform for observability, traces, metrics, evals, prompt management, datasets, and playground workflows.

37.7K4.3KSource-available
tracesevalscosts
#4In spirit
Agents

LangGraph

langchain-ai/langgraph

A framework for building resilient stateful agents with explicit graphs, persistence, human-in-the-loop flows, and controllable execution.

45.2K7.8KMIT
agentsstateworkflows
#5Direct
Evaluation

promptfoo

promptfoo/promptfoo

A CLI and CI workflow for testing prompts, agents, and RAG systems across models, with evals and red-team style checks.

27.5K2.8KMIT
prompt-evalscirag
Related feed

More source-linked context

InfoWorld source artwork
long-formI
long-form

The strangest developer productivity metric of all time

Matthew Tyson argues token burn is a worse productivity measure than lines of code, pointing at Meta's Claudeonomics leaderboard, which ranked the top 250 of over 85,000 employees and drove 60.2 trillion tokens in 30 days.

tokenmaxxingmetricsscoreboards
Read note
Generated Tokenmaxxing editorial thumbnail for ‘Tokenmaxxing’ Is the New Quiet Quitting—Here’s the Fix - SUCCESS Magazine
newsSM
news

‘Tokenmaxxing’ Is the New Quiet Quitting—Here’s the Fix - SUCCESS Magazine

SUCCESS argues tokenmaxxing-style adoption targets create performative AI usage. Their fix is to measure outcomes and quality, not raw token volume.

tokenmaxxingexplainerworkplace-ai
Read note
Generated Tokenmaxxing editorial thumbnail for Amazon employees admit to using AI unnecessarily to pump up internal usage scores — workers complain of intense pressure to use AI tools - Tom's Hardware
newsTH
news

Amazon employees admit to using AI unnecessarily to pump up internal usage scores — workers complain of intense pressure to use AI tools - Tom's Hardware

Amazon's internal AI usage targets can turn into tokenmaxxing: employees run unnecessary tasks in agent tools to climb dashboards rather than ship better work.

tokenmaxxingexplainerworkplace-ai
Read note