> ## 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.

# Automate reviewed CRM changes

> Ask your agent to automate only reviewed CRM changes.

[Agent guide: CLI and SDK instructions →](/docs/guides/crm-workflow-automation)

## 1. Have your context ready

Have the target CRM records, permitted fields, source precedence, and approval owner.

## 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 Design a Deepline CRM workflow for the changes I describe. Inspect live record and property contracts. Preserve current values and source IDs. Propose deterministic changes separately from judgment calls, with field-level evidence and exceptions. Test a small sample with writes disabled in the authored logic. Show the intended changes and read-back checks before requesting permission to apply them.
```

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 approved fields change on the intended records and read back correctly. A changed workflow must not silently overwrite newer trusted data.

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 reading before writing make a concurrent update atomic?

> **Show the answer**
>
> No. Another writer can change the field between operations. Use the
> destination's supported conflict policy or reconciliation.

## Related guides

* [Write Plays](/docs/human/sdk-v2/plays)
* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)
* [CRM data quality automation: validation and safe writes](/docs/human/guides/crm-data-quality-automation)
* [Production Play Integration](/docs/human/sdk-v2/production-integration)


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