Skip to main content

​
What Can You Do with the Landbase CLI?

Landbase CLI turns GTM outcomes into commands you can run from a terminal, Claude Code, Codex, or your own scripts. Choose the path that matches what you want to accomplish:If you have not installed the CLI yet, start with Install Landbase CLI. For agent-led work, see Use Landbase CLI in Claude Code and Codex.Most commands return JSON, which makes the CLI easy for agents and scripts to read. When something goes wrong, the CLI returns a stable error code so your workflow can recover or ask for the right fix.

​
Find audiences with natural language

Use the CLI when you want Landbase to build a company or people audience from a plain-English request.
You can also use the explicit search command:
This is the fastest path when you want an agent to:
  • Find companies or contacts that match a market, role, location, industry, or signal.
  • Save the results to a local file.
  • Pass the dataset into another script, notebook, dashboard, or app.

​
Use Advanced Dataset Creator for precise audiences

Most searches can use the default agent. When you need custom SQL, aggregations, exact filters, ratios, or output columns, use --agent=advanced_dataset_creator.Advanced Dataset Creator is especially useful for searches like:
  • Companies where one team’s headcount is low relative to another team’s headcount.
  • Accounts from an uploaded list that match a computed condition.
  • Rankings, counts, or breakdowns that need aggregation.
  • Prospect lists where the output columns need to be defined in the prompt.
It uses a two-step flow. First, ask for the dataset and reuse a session label:
Then confirm the proposed query in the same session:
Add --session=<label> when you want follow-up prompts to continue the same conversation.
This is useful when you want to start broad, inspect what came back, and then tighten the audience without starting over.

​
Download results in the format you need

The --download flag writes search results to disk. If you do not pass a path, it defaults to ./results.jsonl.The file extension controls the output:Published files can take a few minutes because Landbase runs a publish workflow before the download is ready.

​
Match a person or company

Use match when you have one record and want Landbase to find the best corresponding person or company.
This is helpful for record cleanup, CRM matching, deduplication, and workflows where you need to turn partial information into a Landbase match.

​
Choose an enrichment path

Choose the command based on the input you have and where you want the result to go:Use enrich for one-off lookups, workflow contact-enrich for contact discovery, and workflow enrich when you need repeatable, dataset-scale processing. The commands are not interchangeable: they accept different inputs and produce different kinds of output.

​
Enrich a record

Use enrich when you already have a person or company identifier and want more fields back.
You can request company fields, person fields, or both. If you pass a person identifier, the CLI can automatically resolve the related company and return company enrichment too.

​
Enrich contacts with email and phone

Use the dataset workflow when you have a dataset of known contacts and want asynchronous email or phone enrichment. The removed contact-enrich submit|get command no longer accepts raw JSONL leads; see the migration reference.
Both email and phone enrichment run by default. Use --enrich-phone for phone-only opt-in behavior, or use the explicit --enrich-email and --enrich-phone flags when selecting channels. The workflow creates an enriched child dataset and returns a workflow run ID for polling.
Use --overwrite-existing to replace existing contact values. Use --row-slice=START:END to process a half-open slice of rows; run slices serially and recombine them with workflow union without dedupe keys.

​
Upload your own spreadsheet

Use upload to bring a CSV or Excel file into Landbase as a dataset.
The command returns a dataset ID. You can use that ID to run workflows such as onboard, match, enrich, publish, and download.

​
Select an account, onboard, and import contacts

In platform mode (the default), some commands run against a specific Landbase account. Pick which account the CLI uses, fill in its onboarding profile, and bulk-import contacts from a dataset.First, sign in and choose the account. Run account set with no arguments to pick from a list — your choice is saved, so this is a one-time step per machine:
Fill in the account’s onboarding profile. Run get to see which fields are still needed, then submit a partial payload:
Import the contacts in a dataset into the active account under a tag. --watch blocks until the import finishes and prints a summary of what landed:
To target a different account for a single command without changing the saved one, pass --account=<id>.

​
Launch outbound campaigns

Create and launch outbound email and LinkedIn campaigns against an imported tag. Both channels share the same shape — create a draft, then launch. A template-mode campaign carries one shared message per step and is ready to launch immediately:
For per-contact copy, create in personalized mode and fill the exported audience CSV before launching: audience → fill subject_i/body_i (email) or message_<order> (LinkedIn) → messages → coverage → launch. Sending inboxes and LinkedIn accounts are connected in the web app. See How to launch a campaign.A campaign can also be assigned to a teammate so their inboxes or LinkedIn account send: list assignable users with account users, then pass assignedUserId at create time or re-assign the draft with assign --campaign <id> --user <identityId>. Launching a campaign assigned to someone other than its creator asks for --yes. See the email-campaigns and linkedin-campaigns references.

​
Create dialer sessions

Turn an imported contact tag into a calling session. The JSON definition names the tag through audience.tagName or audience.tagId, controls enrichment, and can assign the session to a teammate with assignedUserId.
Use account users to find the optional assignedUserId; omit it to own the session yourself. status returns the owner and live contact counts grouped by dial status. See the dialer-sessions reference.

​
Manage datasets

Use dataset commands when you need to list, inspect, download, trace, or delete datasets in your workspace.
lineage is especially useful after workflows because it helps you find the child dataset created by a publish, enrich, match, onboard, or sketch run.

​
Run batch workflows

Use workflow commands when you want Landbase to process an existing dataset.
Add --wait when you want the command to block until the workflow completes. Without --wait, the CLI returns a workflow run ID that you can poll with workflow status.

​
Chain commands into a full pipeline

A typical workflow is upload, onboard, publish, find the published child dataset, and download it.
For search results, you can do the common conversion in one command:
For dataset-scale contact enrichment, first upload and onboard a CSV or Excel file, then run workflow contact-enrich on the onboarded dataset. Use workflow wait to recover the output dataset ID before continuing to publish or download.

​
Inspect previous agent runs

Use runs when you need to review prior agent runs for a session.
Pass the same session label you used with --session, or use the raw session_id returned by a search response.

​
Authenticate and stay current

Use auth to sign in, check which key is active, paste an API key, or clear the locally stored key.
Add --force to re-authenticate even when a valid session already exists — useful when a stale session keeps causing errors.Use update to self-update to the latest release:

​
Read outputs safely

Search commands return a structured response with fields such as run_id, session_id, status, content, dataset_id, and created_at.Other commands return the relevant endpoint JSON directly. When you only need a single value, pipe the output through jq:

​
Common options

​
Failure codes

Errors are printed to stderr as JSON so agents and scripts can branch on error.code.