# Adding custom questions

Kyloe AI NoteTaker allows you to add custom screening questions that run automatically during calls with candidates or contacts, capturing responses and mapping them directly to Bullhorn fields for seamless data integration. This feature enhances your recruitment workflow by extracting key data points like availability or preferences in real-time.

#### Follow these steps to create and map a new screening question:

1. First you need to access to the Kyloe AI Manager
2. Navigate to the menu on the top left hand side corner and open the menu
3. Select ***Add questions***
4. Click ***+ Create new question***
5. Now choose the entity you want to add the question to: **Contact** or **Candidate**.
6. Enter the screening question that Kyloe will use to identify and capture the response during calls.
7. In the **Destination** field (optional) you can specify the Bullhorn target field where you want to sve the information to (e.g., `bullhorn.Candidate.availability`).​ Please note destination is not mandatory, you can have a question without updating the answer into a Bullhorn field.
8. Click **Save** to activate the question and lock the mapping.​

<div data-with-frame="true"><figure><img src="/files/O5C7dW6HedJfwT2049DT" alt=""><figcaption></figcaption></figure></div>

#### Best Practices <a href="#best-practices" id="best-practices"></a>

* Use precise phrasing for questions to ensure accurate detection on candidate or contact calls.​
* Test mappings with sample calls to verify data writes back correctly to Bullhorn.​


---

# 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://help.kyloepartners.com/kyloe-ai-notetaker/kyloe-ai-notetaker-admin-guide/adding-custom-questions.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.