# Get to Know Your AI Agent

## AI Agent Overview

Agentic Platform is designed to comprehend and respond instantly to highly specific questions using a combination of advanced natural language processing (NLP) and generative AI capabilities. It utilizes large language models (LLMs) for flexibility and efficiency, ensuring effective communication with users while maintaining brand control.

{% embed url="<https://youtu.be/kxogDPZ2MKc>" fullWidth="true" %}

<figure><img src="https://167344003-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsxN9AGLZMIc5C8dx3zU7%2Fuploads%2Fbw8zaJJTJ3N77KiJutoS%2FScreenshot%202025-05-20%20at%2012.47.32%E2%80%AFPM.png?alt=media&#x26;token=90f9c5bd-c29e-48f3-8e4e-66e351e35100" alt=""><figcaption><p>The infrastructure of your AI Agent Engine</p></figcaption></figure>

### How the AI Agents Work

1. The user initiates the conversation by sending a message.
2. Our platform employs vigilant moderation for 11 categories of inappropriate inputs, including those related to violence, harassment, and hate speech.
3. The Agent analyzes the user intent and directs the message to one of four possible response types:
   * [**Generated Responses**](https://docs.satisfilabs.com/resource-center/manage-your-content/response-types/generated-responses)
     * Answers that are generated by the LLM model using data from your website, documents, or feeds.
     * Generated Responses will be moderated for offensive language and hallucinations.
   * [**Prewritten Responses**](https://docs.satisfilabs.com/resource-center/manage-your-content/response-types/prewritten-responses)
     * Prewritten answers are written in advance by you and surfaced to the user exactly as written.&#x20;
     * Prewritten answers take precedence over generated responses.
   * [**Live Agent**](https://docs.satisfilabs.com/resource-center/bridge-live-chat/get-to-know-bridge)
     * For intents that require a live agent, users can escalate their conversation via the Live Agent.
   * **Security Alerts**
     * When offensive content is flagged, you can provide a custom-prewritten answer or a silent response.
     * In the event that a direct threat is detected, the system triggers an email alert to your chat's admins.
4. Both Generated and Prewritten Responses can have enrichments like buttons, quick replies, images, and videos.
   * Generated Responses can be [**enriched**](https://docs.satisfilabs.com/resource-center/manage-your-content/response-types/enriched-responses) with actionable items (buttons, quick replies, images) through the request portal.
   * Prewritten Responses can be enriched with actionable items (buttons, quick replies, images, gifs, and videos) directly in the response editor.
5. The response is sent to the user.


---

# 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.satisfilabs.com/resource-center/ai-agent-engine/ai-agent-engine-basics/get-to-know-your-ai-agent.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.