# New Custom Prompt

You have the ability to create custom prompts if you need even more personalized icebreakers. 

{% hint style="info" %}
**You do not need to create custom prompts.** The default prompts are proven prompts for effective personalization. Only use this feature if you have a specific use-case that requires additional personalization. 
{% endhint %}

1. Navigate to the [Integrations](https://www.big-brain.co/app/data-cleaning#integrations) tab of the data cleaning app. 
2. Select the "Open AI" tab.
3. Select the "New Custom Prompt" tab.
4. Fill out the type of personalization

{% hint style="success" %}
Valid inputs are "**Company**," "**Location**," "**Headline**," or "**School**." This determines which fields the bot uses to create the icebreaker.
{% endhint %}

5. Write a a custom prompt.

{% hint style="info" %}
For best results, include a list of what you don't want to do, as well as example inputs and outputs for what you'd consider a successful personalization. 
{% endhint %}

{% hint style="warning" %}
Do not create multiple custom prompts for the same type of personalization. IE do not create two Location prompts. Either edit your existing prompt with the same type, or delete it and create another one. **If you enter multiple prompts with the same type only one of them will be used.** 
{% endhint %}

<figure><img src="/files/wtefeYEGxPM1Qi9kSjdU" alt=""><figcaption><p>Write a new custom prompt.</p></figcaption></figure>

6. Click "Create Custom Prompt" to save.


---

# 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/new-custom-prompt.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.