Levered Docs
CLI

Commands

Complete reference for all CLI commands

All commands support --json for structured output unless noted otherwise. Use levered <command> --help for inline documentation on any command.


Authentication

Manage your session and credentials.

CommandDescription
levered login [--api-url URL]Authenticate via browser OAuth. Optionally override the API URL for this session.
levered logoutClear stored session tokens for the current environment.
levered whoamiPrint the currently authenticated user and organization.

Configuration

Read and write CLI settings stored in ~/.levered/config.json.

CommandDescription
levered config listPrint all configuration key-value pairs.
levered config get <key>Print the value of a specific key.
levered config set <key> <value>Set a configuration value.

Optimizations

Create, manage, and inspect optimizations.

List optimizations

levered optimizations list [--limit N] [--include-archived] [--json]

List optimizations in the current organization. Returns the most recent optimizations, up to --limit (default 10). Archived optimizations are hidden unless --include-archived is set.

Show optimization details

levered optimizations show <id> [--json]

Print full details for a single optimization, including design factors, model configuration, linked metric, and current status.

Create an optimization

levered optimizations create \
  --name NAME \
  --design-factors JSON \
  --reward-metric-id UUID \
  [--model-type cmab] \
  [--context-factors JSON] \
  [--json]

Create a new optimization and start training.

FlagRequiredDescription
--nameYesHuman-readable name for the optimization.
--design-factorsYesJSON array of factors and their levels.
--reward-metric-idYesUUID of the metric that defines success.
--model-typeNoModel type. Default: cmab (contextual multi-armed bandit).
--context-factorsNoJSON array of context factors for personalization (e.g., country, device).

Example -- create a hero section optimization with two design factors:

levered optimizations create \
  --name "Landing Page Hero" \
  --design-factors '[
    {"name": "headline", "levels": ["Ship faster", "Build better", "Scale up", "Go live today", "Start free"]},
    {"name": "cta_text", "levels": ["Get started", "Try it free"]}
  ]' \
  --reward-metric-id 8a3b12c4-5678-4def-abcd-1234567890ab \
  --context-factors '[{"name": "country"}, {"name": "device_type"}]' \
  --json

Update optimization status

levered optimizations update <id> --status {live|completed|archived}

Transition an optimization to a new status. See Optimizations for the status lifecycle.

Archive an optimization

levered optimizations archive <id> [-y]

Archive an optimization. Prompts for confirmation unless -y is passed.

View results

levered optimizations results <id> [--json]

Print performance results for an optimization, including estimated lift over the baseline, confidence intervals, and factor importance rankings.

List observations

levered optimizations observations <id> [--page N] [--size N] [--json]

Paginate through the raw observation data (exposures matched to rewards) for an optimization.

FlagDefaultDescription
--page1Page number.
--size20Number of observations per page.

Models

Inspect and manage the bandit models behind optimizations.

CommandDescription
levered models list [--limit N] [--include-archived] [--json]List models in the organization.
levered models state <id> [--json]Print the current model state: variant probability distributions and expected reward per variant.
levered models delete <id> [-y]Delete a model. Prompts for confirmation unless -y is passed.

Warehouse

Inspect and query your data warehouse. Warehouse connections are managed through the dashboard or the API.

CommandDescription
levered warehouse status [--json]Show the current warehouse connection status and provider.
levered warehouse tables [--json]List all tables in the connected dataset/schema.
levered warehouse columns <table> [--json]List column names and types for a table.
levered warehouse preview <table> [-n N] [--json]Preview rows from a table. Default: 10 rows.
levered warehouse query <sql> [-n N] [--json]Run an arbitrary read-only SQL query. Default limit: 100 rows.

These commands are especially useful for AI agents that need to discover table schemas before writing metric SQL.


Metrics

Define reward metrics that tell Levered what counts as a successful outcome.

List metrics

levered metrics list [--json]

Create a metric

levered metrics create \
  --name NAME \
  --sql SQL \
  --anonymous-id-col COL \
  --timestamp-col COL \
  [--value-col COL] \
  [--reward-type TYPE] \
  [--json]
FlagRequiredDescription
--nameYesHuman-readable metric name.
--sqlYesSQL query that returns reward events from your warehouse.
--anonymous-id-colYesColumn in the query result that identifies the user (anonymous ID).
--timestamp-colYesColumn with the event timestamp.
--value-colNoColumn with a numeric reward value. Omit for binary (conversion) metrics.
--reward-typeNoReward type (e.g., bool, numeric).

Example -- create a sign-up conversion metric:

levered metrics create \
  --name "Sign-ups (7d)" \
  --sql "SELECT anonymous_id, signed_up_at FROM analytics.sign_ups WHERE signed_up_at >= CURRENT_DATE - 7" \
  --anonymous-id-col anonymous_id \
  --timestamp-col signed_up_at \
  --json

Preview metric data

levered metrics preview <id> [--limit N] [--json]

Run the metric's SQL query and display a sample of matching rows. Useful for verifying the query returns the expected data before linking the metric to an optimization.

Delete a metric

levered metrics delete <id> [-y]

Delete a metric. Prompts for confirmation unless -y is passed. Metrics linked to active optimizations cannot be deleted.


Variant Serving

Request a variant assignment for a user outside of the SDK.

levered serve <optimization-id> [--anonymous-id ID] [--context JSON] [--json]
FlagDescription
--anonymous-idThe user's anonymous ID. If omitted, a random ID is generated.
--contextJSON object of context factor values for personalized serving (e.g., '{"country": "US", "device_type": "mobile"}').

Returns the selected variant -- the set of factor-level assignments -- for the given user and context.


Interactive Dashboard

levered dashboard [--refresh SECONDS]

Launch a terminal UI (TUI) that displays live optimization data, including variant distributions, reward rates, and model state. The display refreshes on the interval specified by --refresh (default: 10 seconds).

This is a read-only view. Use it to monitor running optimizations without leaving the terminal.