# Artificial Intelligence

Starting way back in 2006, I worked with Artificial Intelligence using the A.L.I.C.E. AIML framework developed by Dr. Richard S. Wallace. I worked to develop a C++ implementation of the A.L.I.C.E. framework, implementing both default AIML datasets as well as developing custom data sets to train the AI on, giving it added resources and "knowledge" to work with, as well as designing personalities and personal traits for the AI. 

Beyond the AI itself, the application also used a visual UI to increase the complexity of the visuals as the AI "worked". Adding a layer to the experience. My goal was to create an implementation that ran on Windows, that anyone could use without prior experience. Simply open and type.

This application ended up going by the monicker of Debbie, though users could import one of many prebuilt or custom personalities.

After this implementation of "C++ Alice", I continued my work with AIML datasets and implemented a PHP version, codenamed PHilliP. This implementation worked well, and I had decided to use it in a more interesting way than a simple chat site. I integrated PHilliP into our current Forum/Message Board software. Giving it it's own user account, and allowing it to reply to any posts within a specific forum. This led to thousands of public discussions from users all over the world. It also increased engagement and revenue for the website through Google Advertising and affiliate marketing.

Jumping to current times, AI has evolved far past simple data parsing and OpenAI has started a revolution in conversational AI. Through my research and current client work, I have worked with GPT-3, GPT-4, as well as developed custom LLMs that can run locally for private industries such as healthcare. Through my work with Mayu, I have integrated LangChain into these processes, allowing both local and remote LLMs to parse through documents and databases. I assisted with creating and hosting a workshop teaching industry professionals how to use LangChain with OpenAI services at the Chicago mHUB.  

<figure><img src="/files/Eig8K2vuWFBh2nzp6u3p" alt=""><figcaption></figcaption></figure>


---

# 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://mikethetech.gitbook.io/mikethetech.com/projects/artificial-intelligence.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.