CLI

The promptic CLI mirrors the full Python API with human-readable table output. All list commands support --json for machine-readable output.

Authentication

# Interactive login (opens browser)
promptic login

# Save API key directly (CI/CD)
promptic configure --api-key "pk_live_..."

# Log out
promptic logout

Workspace

promptic workspace info          # Show current workspace
promptic workspace list          # List all workspaces
promptic workspace select        # Switch workspace (interactive)

Components

promptic components list
promptic components create <name> [--description "..."]
promptic components get <component-id>
promptic components delete <component-id>

Experiments

promptic experiments list [--component <id>] [--status pending|running|completed|failed]
promptic experiments create <component-id> <target-model> [options]
promptic experiments get <experiment-id>
promptic experiments update <experiment-id> [--name "..." --description "..."]
promptic experiments delete <experiment-id>
promptic experiments start <experiment-id>

# Clone an experiment (observations + evaluators) under the same component.
# By default starts from the source's initial prompt; use --initial-prompt to override.
promptic experiments duplicate <experiment-id> [--initial-prompt "..."] [--start]

# Clone an experiment and seed the new initial prompt from the source's
# best optimized iteration — useful to chain optimization runs.
promptic experiments continue <experiment-id> [--start]

Create options

Flag	Description	Default
`--task-type`	`classification`, `textGeneration`, `structuredOutput`	`classification`
`--provider`	`openai`, `openrouter`, `custom`, `google`	`openai`
`--optimizer`	`promptic`, `prompticV2`, `miproV2`, `bootstrapFewShot`, `gepa`	`prompticV2`
`--initial-prompt`	Starting prompt text	—

Observations

promptic observations list <experiment-id>
promptic observations add <experiment-id> --variables '{"message": "..."}' --expected "..."
promptic observations delete <experiment-id> <observation-id>

Evaluators

promptic evaluators list <experiment-id>
promptic evaluators add <experiment-id> --name "..." --type f1|referenceJudge|comparisonJudge|generalJudge|similarity|structuredOutput [--weight 1.0]
promptic evaluators delete <experiment-id> <evaluator-id>

Iterations

promptic iterations list <experiment-id>
promptic iterations get <experiment-id> <iteration-id>
promptic iterations best <experiment-id>

Deployments

promptic deployments status <component-id>
promptic deployments deploy <component-id> --experiment <experiment-id>
promptic deployments prompt <component-id>
promptic deployments undeploy <component-id>

Traces

promptic traces list [--status ok|error] [--limit 50] [--offset 0]
promptic traces get <trace-id>
promptic traces stats [--days-back 30]

Datasets

promptic datasets create <component-id> <name> [--description "..."]
promptic datasets list <component-id>
promptic datasets get <component-id> <dataset-id>
promptic datasets delete <component-id> <dataset-id>

Runs

promptic runs create <component-id> <dataset-id> [--name "..."]
promptic runs list <component-id>
promptic runs get <component-id> <run-id>
promptic runs delete <component-id> <run-id>

Annotations

promptic annotations create <component-id> <run-id> <trace-db-id> [--rating positive|negative] [--comment "..."]
promptic annotations list <component-id> <run-id>
promptic annotations delete <component-id> <run-id> <annotation-id>

Evaluations

promptic evaluations run <component-id> --dataset <dataset-id> [--run <run-id>] [--name "..."]
promptic evaluations list <component-id>
promptic evaluations get <component-id> <evaluation-id>

Global options

All list commands support --json for JSON output:

promptic components list --json
promptic traces list --json | jq '.[] | .traceId'

On this page