> ## 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.

# How to Run Waterfall Enrichment in Claude Code (2026)

> Ask Claude Code to run a reviewed email waterfall for a file.

[Agent guide: CLI and SDK instructions →](/docs/guides/waterfall-enrichment-claude-code)

## 1. Have your context ready

Have a CSV with source IDs, available person identifiers, and an email acceptance rule.

## 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 in Claude Code to prepare an email-waterfall workflow for this file. Follow the supported setup if needed. Inspect the current maintained routes and choose the one that fits the actual identifiers. Prepare a representative pilot with CSV-safe record selection. Preserve validation evidence and unresolved rows, estimate applicable usage, and wait for approval before running. Do not assume an undocumented provider sequence.
```

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 pilot meets the acceptance rule and its usage is scoped to the saved run. Expand the reviewed method only after checking coverage and rejected records.

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

Can two provider comparisons use different acceptance rules and still report comparable accepted-result cost?

> **Show the answer**
>
> No. Hold the population and acceptance rule constant. Otherwise the
> denominator measures different outcomes.

## Related guides

* [Evaluating an enrichment waterfall](/docs/guides/b2b-data-enrichment-waterfall)
* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)
* [Understanding enrichment cost](/docs/guides/enrichment-cost-optimization)
* [Understanding provider consolidation](/docs/guides/gtm-provider-consolidation)


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