> ## 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.

# Personalize Outbound with a Deepline Play

> Ask your agent to prepare evidence-based outreach drafts for review.

[Agent guide: CLI and SDK instructions →](/docs/plays/play-personalize-outreach)

## 1. Have your context ready

Have target accounts or contacts, an approved audience definition, suppression rules, and message constraints.

## 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 Prepare personalized outreach drafts with Deepline for this small target sample. Inspect supported research and contact workflows. Establish identity, preserve evidence, and distinguish facts from hypotheses. Apply suppression and deduplication before preparing drafts. Return the source, proposed message, rationale, and unresolved questions. Explain provider work and wait for approval before executing it. Do not send messages or activate a campaign.
```

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

Each draft uses relevant, supported facts about the intended recipient. A researched draft is not permission to contact the person.

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 observing an account signal prove that the prospect has the pain stated in your draft?

> **Show the answer**
>
> No. Preserve the observation and frame unsupported needs as questions. Do not
> invent a customer statement.

## Related guides

* [Signal playbooks](/docs/human/plays/signal-playbooks)
* [Job changes and CRM cleanup](/docs/human/plays/play-job-change-alerts)
* [SMB and local-business data reference](/docs/features/smb-data-sets)
* [Find Decision Makers](/docs/human/plays/task-find-decision-makers)


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