# How does message generation work?

Hyperscale pairs proprietary models with frontier large language models from leading AI labs to draft a personalized message for every prospect in a campaign.

For each lead, the system:

* Gathers public profile data — headline, role, company, recent activity, summary
* Prompts the model with that context plus your campaign brief
* Drafts a message tailored to that specific prospect

The system also adapts to you over time. As you edit drafts before they send, and as we see which messages get replies, your campaigns sound more like you and convert better.

If you want to dial in the tone before you launch, see [How to Draft Emails](/start-campaigns/start-a-campaign/how-to-draft-emails.md).

**You can always edit, rewrite, or skip any draft before it sends — see** [Can I control the messages I send out?](/faq/can-i-control-the-messages-i-send.md)**.**


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.gethyperscale.com/faq/how-does-message-generation-work.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.