> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Search and save free company data

> Ask your agent to review company snapshot matches before saving them.

[Agent guide: CLI and SDK instructions →](/docs/recipes/search-free-companies)

## 1. Have your context ready

Have normalized target domains or a narrowly defined segment, plus the company fields you need.

## 2. Ask your agent

Paste this into your agent, then provide your task and example inputs when it asks:

```deepline-prompt theme={null}
/deepline-gtm Use Deepline’s free company snapshot to resolve this target list or segment. Inspect the documented fields and query limits. Prefer exact identifiers before broad candidate matching. Preserve original input IDs and explicitly reconcile unmatched domains. Treat employee count as the source size-bucket upper bound, not live exact headcount. Show a bounded read-only result first; ask before saving rows into my workspace database.
```

Complete any requested sign-in yourself. Give the agent the missing information before approving execution. Provider-backed work can incur usage.

## 3. Review the result

The snapshot result is distinguished from live web discovery and workspace writes. Missing domains are reconciled against the input rather than silently omitted.

Ask your agent:

```deepline-prompt theme={null}
/deepline-gtm Compare the result with the acceptance rule we agreed. Show the evidence for accepted and rejected outcomes, unresolved questions, and recorded Deepline usage where work ran. If work is still running or a response is uncertain, inspect the original saved execution before proposing another request. Explain the next decision I need to make.
```

Approve a larger job, recurring work, or external changes only after reviewing that decision.

## Check your understanding

Does finding a company in the free directory automatically write it to your workspace Database?

> **Show the answer**
>
> No. Source retrieval and customer-table persistence are separate operations.

## Related guides

* [Free Company Search Database](/docs/free-company-search-database)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.