# How to match answers with visuals

Twise will only be able to find images or visuals, videos etc, that have clear descriptions and/or instructions for when they should be shown.

<figure><img src="/files/AXhA3IzMOVUOcMQWQey1" alt=""><figcaption><p>See the instructions field</p></figcaption></figure>

&#x20;A trick is to place the exact question that a user might have inside the Instructions box so that the Ai can find it.&#x20;

You can also add a description, for example: *An image of a website widget.*

### How can you make sure that some images are not shown? Or avoid them being shared at the wrong place?

Try updating the Instructions field to either something very specific that will avoid it being show for more general queries.&#x20;

Example: if you have an image of a house the more specific you are in the instruction the clearer the AI will understand when to show it and when not.

Avoid generic instructions such as: an image of a person

Instead try: An image of a young man, holding a sign, that illustrates how product helps


---

# 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.twise.ai/content/how-to-match-answers-with-visuals.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.