Wattage: A token-spend profiler and cost-regression gate for AI agents
Wattage is a new developer tool designed to profile token usage and costs for AI agents. It allows developers to identify inefficient prompt patterns and prevent excessive spending by integrating cost-regression checks into CI/CD pipelines.
Why it matters
As AI agent complexity grows, cost management and token efficiency are becoming critical operational requirements for software engineering teams.
A Kill-A-Watt meter for your AI agents. Point it at a trace and it tells you exactly where your tokens are being burned and wasted, prices each waste pattern in real dollars, prescribes a fix, and can fail your CI when a change makes your agent measurably more expensive.
A real captured agent trace (see provenance ) — Wattage catches a stable prompt prefix being re-sent instead of cached, prices the waste, and prescribes the fix. Regenerate this GIF with vhs docs/assets/demo.tape (see the tape file for the exact command).
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in