# Manual content creation

Now that we've covered what contents are and why they're useful, let's look at how to create them. First, let's go over the structure of a content — what fields it has and what they're for.

### Content structure

A content in AIsuru is organized into clearly labeled sections in the interface. Don't worry — we'll go through all of them in the following pages.

* **Question** (text, required): the main question that will trigger this content;
* **Question variants** (multiple text): other ways of phrasing the same question to improve recognition;
* **Answers** (text, required): the main answer and any alternative answers;
* **Assigned to** (dropdown): controls who can see the content ("Public" or specific roles);
* **Non-random** (checkbox): excludes the question from being suggested during user inactivity;
* **Location and date** (buttons): restricts visibility by geographic area or time period;
* **Media** (upload area): space to attach images, videos, or PDFs;
* **Link** (input area): adds external URLs to the answer;
* **Advanced** (expandable sections): suggestions, tags, context variables, code snippets, timeout, and DCM integration.

### How to create a simple content

1. Go to your Agent's management panel;
2. Click on  **Contents** in the sidebar\*\*;\*\*
3. Click the  **New content** button;
4. Fill in the required fields:
   1. **Question** -> enter the question your Agent should answer;
   2. **Answer** -> enter the answer your Agent should give (include all the necessary information).

✅ Done! Click "Confirm" in the bottom right to save your content.

### Other settings

There are other settings that can come in handy in different scenarios. Let's take a look!

#### Question variants

In this section, found just below the question, you can add question variants — that is:

* **Other ways of phrasing the same question** -> "what's the dog's name?" as the question and "what is the dog called?" as a variant;
* **Other questions that have the same answer** -> "Where do I go to renew my ID?" and "Where do I go to renew my ID in Rome?" as a question variant.

{% hint style="info" %} <mark style="color:blue;">Question variants help</mark> <mark style="color:blue;">**AIsuru more easily find the most relevant content**</mark> <mark style="color:blue;">to answer with.</mark>
{% endhint %}

Can't think of question variants? Let AIsuru help: click the  **Suggest variants** button and AIsuru will generate question variants based on the content's answer (which must already be filled in).

#### Additional answers

In this section, found just below the "Answer" field, you can add alternative answers for the same question.

This lets you have "response variants" for each question. For example:

* Question: "What is the capital of Italy?";
* Answer: "Rome";
* Additional answer: "The capital of Italy is Rome";
* Additional answer: "The capital is Rome".

If a user asks your Agent "What is the capital of Italy?" they might receive any of these responses: "Rome", "The capital of Italy is Rome", or "The capital is Rome".

{% hint style="info" %} <mark style="color:blue;">Add additional answers if you're not heavily relying on generative AI but still want to</mark> <mark style="color:blue;">**reduce repetitiveness and make your Agent's interactions feel more natural**</mark><mark style="color:blue;">.</mark>
{% endhint %}

Just like with question variants, you can also let AI suggest additional answers: click the  **Suggest answer** button and AIsuru will generate an answer based on the question (which must already be filled in).

#### Media and links

You can add media and links to your contents:

* Media -> images, videos, and PDF documents;
* Link -> add a URL and customize the page name.

{% hint style="info" %} <mark style="color:blue;">Media and links enrich the Agent's responses, letting it show images or provide additional resources during the conversation.</mark>
{% endhint %}

-> if a user asks "What's the Italian capital?", AIsuru will respond "Rome" (or a variant) and attach the image you added to the answer.

The language model may or may not choose to show media and links when responding to users. You can change this behavior in the [other generative AI settings](/en/generative-ai/advanced/other-generative-ai-settings.md).

#### Other fields

Below the "Assigned to" field, you'll find three important options that affect how the content behaves:

1. **Non-random**: if selected, this prevents the question from being randomly suggested when a user has been inactive for too long. Useful for contents that wouldn't make sense as random suggestions.

{% hint style="info" %}
If you want your Agent to ask users "random" questions, you can enable the "Suggest questions if the user is inactive" toggle in Settings > General > Advanced settings. To learn more, read [how to use timeout](/en/agent-training/advanced/content-customization/using-timeout.md).
{% endhint %}

#### Advanced settings

For more complex settings, head to the dedicated [content customization](/en/agent-training/advanced/content-customization.md) page: there you'll learn how to customize responses by role, date, or location, how to run [code snippets](/en/agent-training/advanced/content-customization/managing-code-snippets.md), and much more!


---

# 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.aisuru.com/en/agent-training/contents/manual-content-creation.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.