Insights
Field notes on AI coding spend.
Practical, referenced writing for CTOs, platform leaders, and FinOps teams — on where AI coding tokens go and how to stop overpaying for them.
Featured guide · 6 min read
Your AI coding bill is mostly reading: where agent tokens go, and how to stop paying frontier prices for them
Coding agents spend most of their tokens pulling code into context, not reasoning about it. That's the part routing makes cheap.
Read the guideLibrary
Showing 4 items
Article · 7 min read
Route, don't upgrade: how model cascades cut enterprise AI spend
A ticket label and a merger analysis shouldn't cost the same per token. Routing sends each task to the smallest model that does it well.
ReadGuide · 5 min read
Proving routed code is as good: a verification playbook
A cost cut that shows up later as bugs isn't a saving. Here's how to check routed work before your engineers depend on it.
ReadReport
The AI Coding Spend Report
How engineering organizations are spending on Claude Code, Cursor, and Copilot, and where the tokens actually go.
Reserve your copyWebinar
Live session: routing AI coding tools in regulated codebases
For platform, security, and engineering leaders in finance and healthcare: cutting AI coding spend when source code can't leave the network.
Register interest
Annual report
The AI Coding Spend Report
How engineering organizations are spending on Claude Code, Cursor, and Copilot, and where the tokens actually go.
Register to receive the report on release and to be invited to contribute to the practitioner survey.
TokenShunt
The AI Coding Spend Report
Annual report
Start the conversation
Stop paying frontier prices for routine work.
Tell us which coding tools your engineers use and roughly what you spend. We'll show you where the tokens go and what routing would change.
We respond within 1 business day. Mutual NDA available before any data discussion.