Skip to main content
The Coval CLI provides terminal access to Coval’s evaluation APIs for scripting, automation, and CI/CD integration.

GitHub Repository

View source, releases, and contribute

​
Quick Start

1

Install the CLI

brew install coval-ai/tap/coval
See Installation for all methods.
2

Authenticate

coval login
3

Launch an evaluation

coval runs launch \
  --agent-id <agent_id> \
  --persona-id <persona_id> \
  --test-set-id <test_set_id>
4

Watch progress

coval runs watch <run_id>

​
Command Reference

Agents

Create, list, update, and delete agent configurations

Runs

Launch evaluations and monitor progress in real time

Simulations

Inspect individual simulation results and download audio

Test Sets

Organize test cases into collections

Test Cases

Define inputs and expected outputs for evaluations

Personas

Configure simulated callers with voice and language settings

Metrics

Define how simulations are scored and evaluated

Mutations

Test agent variations with config overrides

API Keys

Manage API keys for programmatic access

Run Templates

Save reusable evaluation configurations

Scheduled Runs

Schedule recurring evaluation runs

Dashboards

Create dashboards and widgets for monitoring

​
Global Flags

All commands support these flags:
FlagDescriptionDefault
--format <format>Output format: table or jsontable
--api-key <key>Override API key for this command—
--api-url <url>Override API base URL—
--helpShow help for any command—

​
JSON Output for Scripting

Use --format json to get machine-readable output: 
# Get run status
coval runs get abc123 --format json | jq '.status'

# List agent IDs
coval agents list --format json | jq '.[].id'

# Extract simulation transcript
coval simulations get sim123 --format json | jq '.transcript'

​
Requirements