# AI Agent Creation Overview

Follow the steps in the video tutorials below to create your AI Agent one step at a time, or click the links to read through the detailed instructions of each section.

{% stepper %}
{% step %}

#### [Get started with a Quickstart AI Agent](/getting-started-1/quick-start-ai-agents/quick-start-ai-agent.md)

The Quick Start AI Agent is an optimised journey that really simplifies the process of creating an AI Agent. It is the fastest way to get up and running with OpenDialog.

{% embed url="<https://youtu.be/RhUc_mgkNl8?si=KoR5D0KO6rPIJ2LL>" %}
Get started with a Quickstart AI Agent
{% endembed %}
{% endstep %}

{% step %}

#### [Add a new topic of discussion](/tutorials/add-a-new-topic-of-discussion.md)

Adding new topic of discussion allows your AI agent to answer questions and engage in conversations beyond the initial scope, creating a more dynamic and comprehensive user experience.

{% embed url="<https://youtu.be/v6wBulsRa4o?si=y75reHmgUXuX-ZEV>" %}
Add a new topic of discussion
{% endembed %}
{% endstep %}

{% step %}

#### [Add & use knowledge sources via RAG](/tutorials/use-knowledge-sources-via-rag.md)

Now, we obviously want our AI Agent to provide more relevant and precise information to our users, using dynamic responses based on your own knowledge sources.

{% embed url="<https://youtu.be/EwM5A6QNEFA>" %}
Add a knowledge source & use it in your conversation design
{% endembed %}
{% endstep %}

{% step %}

#### [Add a structured process conversation](/getting-started-1/quick-start-ai-agents/a-process-handling-ai-agent.md)

Handling processes needs specific attention because they have a well defined series of steps (and sequence) and a well-defined end goal.

{% embed url="<https://youtu.be/ZA7xgNQDYGk>" %}
Easily add a structured conversation thanks to OpenDialog's scalable model.
{% endembed %}
{% endstep %}

{% step %}

#### [Add a 3rd party integration](/tutorials/integrate.md)

Throughout the course of a conversation, we may want to communicate with systems outside of OpenDialog to send or receive data. This may be as simple as a "ping" to a URL representing a milestone in the user's journey, or an integration with an external data source which takes some input data from the conversation, and outputs some new data to return to the conversation.

{% embed url="<https://youtu.be/aseZ5oHG1IQ>" %}
Add a 3rd party integration
{% endembed %}
{% endstep %}

{% step %}

#### [Test and tweak your AI agent](/tutorials/test-and-tweak-your-ai-agent.md)

Your AI Agent is almost ready to launch! Before you publish it, let’s make sure it’s optimised for the best user experience.

{% embed url="<https://youtu.be/OP8V9e3K3u8>" %}
Follow along to go through the different steps to debug your AI Agent's experience
{% endembed %}
{% endstep %}

{% step %}

#### [Publish your AI agent](/tutorials/publish-your-ai-agent.md)

Ready to hit Publish? Amazing! Using OpenDialog's Alias feature, you can easily embed your AI Agent on your website or your application in no time and do A/B testing along the way thanks to it's flexible setup.

{% embed url="<https://youtu.be/CnL88dIvqQE?si=MFun5aJuUWU5ozqr>" %}
Publish your AI Agent walkthrough
{% endembed %}
{% endstep %}
{% endstepper %}


---

# 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.opendialog.ai/tutorials/ai-agent-creation-overview.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.