Data teams

# Give the difficult   data work a fleet.

Trace discrepancies, investigate unexpected results and develop faster implementations.

Built around your project

## More approaches.  Working at once.

Start with the pipeline, query or dataset your team already works on. The fleet can investigate different causes and return queries, checks and proposed changes for the same system.

01 

## Data reconciliation

Trace differences to records, rules and transformations.
[Put a fleet on it ](/use-cases/data-reconciliation/) 

02 

## Performance optimization

Try different implementations against the workloads that cost you time.
[Put a fleet on it ](/use-cases/performance-optimization/) 

03 

## Software correctness

Explore edge cases, reproduce failures and develop regression tests.
[Put a fleet on it ](/use-cases/software-correctness/) 

## 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/)