> For the complete documentation index, see [llms.txt](https://docs.aisuru.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisuru.com/en/agent-training/contents/what-are-contents-and-why-they-matter.md).

# What are contents and why they matter

AIsuru lets you enrich your Agent's knowledge base with precise, personalized information through contents. This feature is essential for building a conversational AI that's truly tailored to your needs.

### What are contents?

"Contents" are **question-and-answer pairs that the Agent uses to respond to users**. Having more contents increases the accuracy and precision of your Agent.

### Why do they matter so much?

When a user asks your Agent a question, it will use all the tools at its disposal to respond:

1. **Contents come first**: if the user's question is very similar to one already in the contents, AIsuru will respond with the answer already saved there;
2. **If AIsuru can't find a matching content, it will pass the most relevant contents to the generative AI**, which will respond based on: [instructions](/en/generative-ai/ai-instructions.md), [relevant contents](/en/agent-training/contents.md) and [functions](/en/advanced-features/integrations/functions.md) [(advanced)](/en/advanced-features/integrations/functions.md).

-> Creating and maintaining contents is essential for **improving the quality of your Agent's responses**.

### Confidence threshold for contents

The **confidence threshold** is a parameter that determines how confident the Agent needs to be that it found the right content before delivering a content-based response.

**How it works:**

* **Low threshold**: the Agent will respond even with content that only partially matches the user's question
* **High threshold**: the Agent will only respond when it's very confident the content is relevant to the request

**When to adjust it:**

* **Raise the threshold** if you notice the Agent giving irrelevant or incorrect answers
* **Lower the threshold** if the Agent says "I don't know" too often, even for questions it should be able to answer

**How to configure it:**

1. Go to your Agent's **Settings**
2. Select the **General** section
3. Find "**Confidence threshold**" and choose the level you want: Very low, Low, Normal, High, Very high

{% hint style="info" %}
**NOTE**:\
Changing the confidence threshold can significantly affect response quality. We recommend testing your Agent carefully after each change and adjusting gradually.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.aisuru.com/en/agent-training/contents/what-are-contents-and-why-they-matter.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.