# Adding FAQs

## Viewing all FAQs / Human Feedback

The AI settings page includes an FAQ section, where you'll find any FAQs that you've either manually added, or ones that have been generated from [human feedback](/docs/ai-configuration/tuning/human-feedback.md) provided on the conversations page.

<figure><img src="/files/VcajqAfYP2fhrpuWHyJH" alt=""><figcaption></figcaption></figure>

## Adding a new FAQ to the Knowledge Base

From here, you can edit existing FAQs, or click "Add FAQ" to add some knowledge manually right from the Alhena dashboard.

<figure><img src="/files/dTAriMmVZJGMS8DD13yk" alt=""><figcaption></figcaption></figure>

## Managing Conflicting FAQs

When any new FAQ is added, we'll mark any that appear to have conflicting information. This will help to avoid any incorrect answers by providing clear information to your AI agent.

<figure><img src="/files/i9XgrkkHwXFAstOFngtf" alt=""><figcaption></figcaption></figure>

When you edit FAQs from this page, we'll show any other FAQs that conflict with that one, along with the reason Alhena thinks these FAQs might be conflicting.

<figure><img src="/files/l0FVgg920ylRMOXxFOxm" alt=""><figcaption></figcaption></figure>

From here, you can keep any of the flagged FAQs that you'd like. You can choose to update them individually or delete ones that you no longer want to be in the system.

All FAQs will be availble to your AI agent, even if we've marked them as conflicting. The conflict flag only is there to help you more easily improve your AI agent's performance.

Here is a video explaining all of this in detail:

{% embed url="<https://www.loom.com/share/a07cfd7d136744d1ac4c7c2973738677>" %}


---

# 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://alhena.gitbook.io/docs/ai-configuration/tuning/adding-faqs.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.