# How AIsuru finds answers

When a user asks your Agent a question, AIsuru uses an **advanced semantic search system** to find the most relevant answer. Understanding how this works will help you optimize your contents for increasingly precise and useful responses.

### The semantic search process

#### 1. Converting to vectors

Every time you create a content or a user asks a question, AIsuru converts the text into a numerical representation called a **vector** (embedding). These vectors capture the semantic meaning of words and phrases, letting the system understand the context and intent behind a message.

#### 2. Similarity search

When a user asks a question, the system:

* Converts the question into a vector
* Compares this vector against all the vectors from your available contents
* Calculates semantic similarity to find the most relevant contents

#### 3. Intelligent response

Based on the search results, AIsuru uses one of two strategies:

**Direct match**: If it finds a very similar question in your contents, it immediately provides the associated answer. This ensures fast, precise responses for common questions.

**Generative AI assist**: If it doesn't find a close match, it selects the most similar contents and passes them to the generative AI, which formulates a personalized response using the most relevant information.

### AIsuru's proprietary NLP technology

This process is powered by **AIsuru's proprietary Natural Language Processing (NLP)**, which offers:

* **Semantic understanding**: goes beyond simple keyword matching to understand the real meaning of questions
* **Linguistic flexibility**: recognizes questions phrased in different ways but with the same meaning
* **Multilingual support**: works effectively across different languages
* **Continuous learning**: constantly improves search accuracy

### Benefits for your users

This advanced system ensures:

* **Precise answers**: always finds the most relevant information
* **Natural experience**: users can ask questions in their own words
* **Fast responses**: optimized process for quick performance
* **Consistency**: maintains response quality even with large volumes of content

### Tips for optimizing your contents

To get the most out of this system:

1. **Vary your questions**: create different variants for the same topic
2. **Use natural language**: write the way your users actually speak
3. **Cover synonyms**: include alternative terms for the same concepts
4. **Test regularly**: check that responses are relevant in real conversations

AIsuru's semantic search system is the technological core that makes your Agents truly intelligent and useful.


---

# 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/how-aisuru-finds-answers.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.