> ## 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 outreach from verified evidence

> Ask your agent to draft personalized messages from checked evidence.

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

## 1. Have your context ready

Have reviewed recipients, relevant source evidence, tone and offer constraints, and suppression rules.

## 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 outbound drafts with Deepline for this approved sample. Establish recipient identity and use relevant, attributable facts. Separate factual observations from hypotheses. Preserve the evidence behind each proposed sentence and apply my suppression rules. Flag weak or stale personalization instead of inventing a trigger. Propose the research pilot and usage before provider work. Do not send or upload messages.
```

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 draft’s claims are supported and relevant to the intended recipient. A plausible message is not enough if its personalization evidence is missing.

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 an inferred problem be presented as something the prospect told your team?

> **Show the answer**
>
> No. Keep inference distinct from a customer statement. Use supported facts and
> a relevant question.

## Related guides

* [Write Plays](/docs/human/sdk-v2/plays)
* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)
* [Personalize Outbound with a Deepline Play](/docs/human/plays/play-personalize-outreach)
* [Sequencer integrations](/docs/human/features/email-sequencer-integration)


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