# [Webinar] What actually cut our AI spend (and what didn't)

Canonical: https://brew.new/templates/infracost/webinar-what-actually-cut-our-ai-spend-and-what-didnt

Brand: infracost.io
Category: event-invitation

![Preview of [Webinar] What actually cut our AI spend (and what didn't)](https://cdn.brew.new/email-preview-55099836b236c8c6-tracking_r57rpj9sn6zc4jz46w22w4ad898gqpmf-1792603256888.png)

## Email content

View this email in your browser

Infracost

Between March and August, our token usage at Infracost grew 4.9x while our AI bill grew 2.4x.

Model routing and compression barely helped. The bigger savings came from an internal agent that reviews every model call in our code and opens pull requests to fix waste. It has cut our product AI spend 45% so far, and in one case it found a model reading the same file 74 times per run. That workload now costs close to nothing.

Alistair Scott, our co-founder and CTO, is walking through how it works in a 30-minute live session, with time for questions at the end.

Oct

27

Tuesday, October 27

8:30 AM PDT / 11:30 AM EDT / 4:30 PM CET

Alistair Scott

Co-founder and CTO, Infracost

Save my spot

If you can't make it live, register anyway and we'll send you the recording.

The Infracost team

P.S. Bring your weirdest AI usage questions. Alistair will answer them live.

Infracost Inc.

2261 Market Street

STE 85821

San Francisco, CA 94114

USA

You signed up at Infracost.

Update your preferences or

unsubscribe.

[Open and remix this design](https://brew.new/templates/infracost/webinar-what-actually-cut-our-ai-spend-and-what-didnt)

[Browse email designs](https://brew.new/browse/templates)