# Create Basic AI Agents

### Prerequisites <a href="#prerequisites" id="prerequisites"></a>

* Ensure that you are logged in to the MOOF application via <https://app.moof.fun/login> before proceeding.
* For optimal performance, we recommend using modern web browsers based on Chromium (e.g., Google Chrome) or Mozilla Firefox.

<figure><img src="/files/gjl0KWKpg4SPk5P02pEr" alt=""><figcaption></figcaption></figure>

### Build from Scratch

**Step 1:** Create a New Folder

This folder will serve as the storage location for all project files associated with this course.

<figure><img src="/files/6s4hF5PCFJTolfXcex4h" alt=""><figcaption></figcaption></figure>

**Step 2: Create Your Own Flow**

Begin by designing a new custom assistant by creating your own flow. This will serve as the foundation for your AI Agent's behavior and responses.

<figure><img src="/files/nAkQu5W68Ln4tJGzpQUY" alt=""><figcaption></figcaption></figure>

**Step 3: Choose a Template to Get Started**

MOOF offers three sample templates to help you begin the journey. For a basic introduction, we recommend starting with the **Simple Agent** template. Once you become more familiar with the platform, you may opt to build from scratch using the **Blank Flow**.<br>

<figure><img src="/files/SYVSbVJmXQlW0oryTQsB" alt=""><figcaption></figcaption></figure>

**Step 4: Customize Your AI Agent**

The **Simple Agent** template includes a set of foundational modules to help you get started:

* **Agent**: The core Large Language Model (LLM) responsible for receiving user input, reasoning, and generating appropriate responses.
* **User Input**: The interface module through which users provide commands or queries.
* **User Output**: The interface module responsible for displaying the agent’s responses to the user.
* **Calculator**: A basic utility module that can be added to extend the agent’s functionality. While primarily used for demonstration purposes, note that the LLM itself is capable of handling basic arithmetic operations without this tool.

<figure><img src="/files/y50YZodxfl996DXerYKr" alt=""><figcaption></figcaption></figure>

**Note:**\
Select an LLM model that best aligns with the objectives of your AI agent. At this stage, users have free access to available **MOOFAI\_API\_KEY** for experimentation and development.

<figure><img src="/files/IZ7XFluVxocaKqGbDonX" alt=""><figcaption></figcaption></figure>

**Step 5: Demo!**

Click on the **Playground** to begin interacting with your AI agent.<br>

<figure><img src="/files/BQiPONbK6AHJWhVPMv97" alt="" width="375"><figcaption></figcaption></figure>

Your AI agent is now ready to use - start by assigning it a task of your choice.

<figure><img src="/files/0ldQWzIlwuCMiRRuhpgP" alt=""><figcaption></figcaption></figure>

From here, the final part of the journey is yours to explore!


---

# 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://moofai.gitbook.io/moof/how-to-use-moof/create-basic-ai-agents.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.