> ## 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.

# Validate Incoming CSV Files Before CRM Enrichment

> Ask your agent to check an input file before enrichment or CRM updates.

[Agent guide: CLI and SDK instructions →](/docs/guides/validate-incoming-csv-files)

## 1. Have your context ready

Have the CSV and the required headers, identifier rules, and duplicate policy for its intended workflow.

## 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 Validate this CSV before Deepline enrichment. Parse quoted commas and embedded newlines correctly. Preserve source row identity. Separate file-level failures from row-level missing fields, invalid formats, and duplicates. Return accepted rows plus a rejection report with reasons. Do not start enrichment or repair the CRM while input requirements remain unresolved.
```

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 accepted and rejected records reconcile to the parsed file. An email format check is not mailbox verification, and physical line counts are not necessarily record counts.

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 a valid CSV header prove every row meets the business acceptance rule?

> **Show the answer**
>
> No. File structure and row acceptance are separate checks. Preserve row-level
> exceptions and their source identities.

## Related guides

* [CRM data quality automation: validation and safe writes](/docs/human/guides/crm-data-quality-automation)
* [Automated Email Verification Before Outbound](/docs/human/guides/automated-email-verification)
* [How to Run Waterfall Enrichment in Claude Code (2026)](/docs/human/guides/waterfall-enrichment-claude-code)


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