Results and files

# Keep what   the fleet builds.

Code, tests, experiments and findings, ready for your agent to bring back into the project.

Returned to your project run / 
01 Code & changesReview and apply
02 Tests & experimentsRun the checks again
03 Findings & activityFollow the investigation
Your agent helps you work through it.

On this page [Use the output ](#section-0) [Look closer when you need to ](#section-1) [Continue from here ](#section-2) [Read as Markdown ](/features/artifacts/index.md) 

## Use the output

The result can be a program, a patch, a notebook, a report or a new dataset. The output follows the problem you set.

## Look closer when you need to

Follow a result into the source files, commands and agent exchanges that produced it. Your team or your own agent can inspect the work.

## Continue from here

Bring the project files into your existing agent session. It can explain changes, rerun tests and help you prepare the work for your codebase. Export contents and retention terms are confirmed before purchase.

[How it works ](/how-it-works/) [Run your first fleet ](/first-fleet/) 

## Put a fleet on your project.

256 agents. Four hours. $1,000 for your first run, with model inference, computers and fleet operation included.

[Explore your first fleet ](/first-fleet/) [Ask your agent what to run ](/evaluate/)