Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token budget — A cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Splitting a fixed token budgetA cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.Full definition → across execution, advising, and grading roles beats spending it all on one bigger executor, lifting a financial-analysis benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → from 76 to 89 for the same cost.
videoEvery step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate
videoHarness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS
videoLoophole: Adversarial Agents To Stress Test Your Morality — Brendan Rappazzo, Morgan Stanley
videoWhy Can't Anyone Answer Questions About the Business? — Garrett Galow, WorkOS
