Practical guide

# Choose the   next thing to try.

Build on what your fleet produced, with your existing agent helping you choose the next step.

On this page [Start with the result ](#section-0) [Give the next run a stronger starting point ](#section-1) [Make fleet work part of the project ](#section-2) [Read as Markdown ](/resources/measuring-a-run/index.md) 

## Start with the result

Ask your agent which changes or findings advance the project. Identify the parts ready for integration and the questions worth another investigation.

## Give the next run a stronger starting point

Reuse the code, test cases and tools from the first run. Include what you learned and the constraints you now understand better.

## Make fleet work part of the project

The monthly plan gives you twenty standard fleet runs. Use them across separate tasks or successive investigations as your project develops.
[Explore the monthly plan ](/pricing/) 

[Getting started ](/docs/getting-started/) [Read with your agent ](/evaluate/) 

## 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/)
