# Open AI

You can personalize outreach messages to contacts with our Open AI integration. Navigate to the [Integrations](https://www.big-brain.co/app/data-cleaning#integrations) tab of the Data Cleaning app. 

<figure><img src="/files/YkiiliCmfJggi3pxuOYP" alt=""><figcaption><p>Open AI Integration</p></figcaption></figure>

You can create personalized icebreakers based on

* Company
* School
* Location
* Headline

## Default Prompts

We have a set of default prompts that are proven to create effective personalized icebreakers.&#x20;

{% content-ref url="/pages/tNtYxOMleShaaOGWGLEV" %}
[Default Prompts](/apps/data-cleaning/integrations/open-ai/default-prompts.md)
{% endcontent-ref %}

## Custom Prompts

If your requirements are more specific, you can also create your own custom prompts. Read more on how to create new custom prompts or edit existing custom prompts below.&#x20;

{% content-ref url="/pages/WuIX3R8wFfIkWUYd8Whh" %}
[New Custom Prompt](/apps/data-cleaning/integrations/open-ai/new-custom-prompt.md)
{% endcontent-ref %}

{% content-ref url="/pages/Hl364VfzO6hrNFTVbSlk" %}
[Existing Custom Prompts](/apps/data-cleaning/integrations/open-ai/existing-custom-prompts.md)
{% endcontent-ref %}

## Connect a Linkedin Account to Big Brain

Since we must scrape the person's profile to get fields to base the personalization on, you must connect a Linkedin account to Big Brain in order to create personalized icebreakers.

{% hint style="success" %}
You must connect a Linkedin account to Big Brain to use the personalization feature.
{% endhint %}

{% content-ref url="/pages/yZZiZaybxmHCo6r9K8Xf" %}
[Connect a New Linkedin Account](/apps/linkedin-outreach/accounts/connect-a-new-linkedin-account.md)
{% endcontent-ref %}

## Use Icebreakers as Text Replacements

Set up your email and Linkedin campaigns with text replacements to create dynamic content that's unique to that prospect and makes your message more relatable.&#x20;

{% content-ref url="/pages/LUgRNbiVJ2kvYokGj2oQ" %}
[Using Icebreakers as Text Replacements](/apps/data-cleaning/integrations/open-ai/using-icebreakers-as-text-replacements.md)
{% endcontent-ref %}

## Add Your Open AI API Key

You can increase the amount of personalized icebreakers you can create by adding your own Open AI API Key.

{% hint style="info" %}
This is optional.
{% endhint %}

{% content-ref url="/pages/5Jnw2YyVttPNuyLKJypB" %}
[Add Your Open AI API Key](/apps/data-cleaning/integrations/open-ai/add-your-open-ai-api-key.md)
{% endcontent-ref %}

## Complete the Data Cleaning Form

Submit the data cleaning form with both "Personalize with AI" and "Linkedin Profile Scraper" selected. Additionally, select "Linkedin Profile Finder" if you do not already have the person's Linkedin profile and we will attempt to find it automatically based on their name, company, and domain.&#x20;

You must enter a Linkedin Account ID for the profile scraper to work and for the bot to be able to personalize the messaging.&#x20;

<figure><img src="/files/BOqXU2jlxpwRamntNXT0" alt=""><figcaption><p>Personalize with AI</p></figcaption></figure>

Finally select which personalizations you'd like to use. You can use more than one at a time. When you submit the form, you can use text replacements for any of the destinations given to dynamically substitute the personalized messages into your outreach messages.

{% content-ref url="/pages/om6dd1ZbHf6z89iUmsTN" %}
[Data Cleaning Form](/apps/data-cleaning/data-cleaning-form.md)
{% endcontent-ref %}


---

# 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.big-brain.co/apps/data-cleaning/integrations/open-ai.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.