Research and innovation leaders

# Try the next scale   of AI on your own work.

Give your team a concrete fleet experiment, with a defined run and work to inspect afterward.

Built around your project

## More approaches.  Working at once.

Choose a question that matters to the business. Use the coding agent your team already knows to prepare the assignment and review the returned work. Start with one fleet before planning a larger program.

01 

## Technical exploration

Build working tests of the approaches you are considering.
[Put a fleet on it ](/use-cases/technical-diligence/) 

02 

## Algorithm search

Implement and compare methods under your constraints.
[Put a fleet on it ](/use-cases/algorithm-search/) 

03 

## Evidence review

Follow claims and contradictions back through the source collection.
[Put a fleet on it ](/use-cases/evidence-review/) 

## Work that returns  to your team.

Your existing agent brings back code, tests and findings from the fleet. Review the changes in the project where you need them, then choose what to ship or investigate next.
[See work from real fleet runs ](/examples/) 

## 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/)