---
title: "About Caveman"
description: "We’re here to make AI agents do better work, with less waste. Less cost. Less"
canonical: https://caveman.so/about
last-updated: 2026-09-16
---

# About Caveman

We’re here to make AI agents do better work, with less waste. Less cost. Less
waiting. Fewer failures.

## A very personal waste problem

By Julius Brussee, founder of Caveman.

I was a student building with AI. Then my AI bill grew to five times what I
spent on groceries.

I wanted to keep building. So I started looking at what I was paying for:
repeated context, long answers, and work the agent had already done. I made a
small fix and put it on GitHub.

Overnight, Caveman reached #1 on Hacker News. A prompt that made agents talk
like cavemen had found a problem a lot of people recognized.

Then enterprises started getting in touch. I worked with them one on one,
helping untangle their own AI waste. The same question kept coming back: how do
we get useful work out of these systems without spending so much money and time
getting there?

That work became the platform. The problem had grown from a student’s budget
to entire agent systems. The reason for building stayed the same.

[The open-source project that started it](https://github.com/JuliusBrussee/caveman)

## The mission: more work worth doing

AI makes more possible. Waste puts a limit on how much of it we can use.

We’re building Caveman to move that limit. To help agents finish the job with
less money, less waiting, fewer failures, and less human intervention.

The goal is continuous improvement: understand where resources go, find a
better way, prove it works, and put it into practice.

### What we optimize for

**Cost per successful agent task.** With quality and reliability held to the
standard the work requires.

Total cost, including every attempt, divided by successfully completed tasks.

### One system. A continuous loop.

1. **Find the waste.** Understand what happened across the whole task.
2. **Try a better way.** Turn that evidence into a change worth testing.
3. **Check the outcome.** Measure cost, speed, quality, and reliability together.
4. **Put it to work.** Roll out proven improvements. Keep learning from the next run.

[Explore the platform](https://caveman.so/products/platform)

## The Caveman way

### Count the whole task.

A cheaper model call means little if it takes eleven attempts to finish the
job. Count the retries, the waiting, and the person who had to step in. The
outcome is what matters.

### Make better prove itself.

An improvement has to survive contact with real work. Test the change against
the task. Check the quality. Measure the total cost. Keep the results that hold
up, and learn from the ones that don’t.

### Earn the right to act.

The goal is less work for the people running agents. Automation should earn
their trust through evidence, clear limits, and changes they can review and
reverse.

[Why we refused a promising benchmark result](https://caveman.so/news/we-cut-26-percent-and-refused-the-claim)

## The ambition got bigger. The idea stayed simple.

why use many token when few token do trick.

## Let’s make more of what AI can do.

If you’re spending too much time or money getting agents to work, we’d like to
hear your story.

[Talk to us](https://caveman.so/contact) or email
[contact@caveman.so](mailto:contact@caveman.so).