Docs

API Reference

Simulation & evals to ship delightful voice & chat AI agents

Easily run Coval evaluations directly from your GitHub repository with customizable inputs.

Understand and analyze your AI agents' performance with Coval's comprehensive metrics

Take part in the hackathons we support and collaborate with us in advancing responsible AI development by testing your agents! 

Integrate Coval into your pipeline seamlessly through our API

Creates a new dataset or identifies an existing dataset by name

Retrieves the status or metrics of a specific run by run_id

Push a transcript for monitoring production transcripts