A simple dictionary that defines the AI buzzwords that've been buzzing you crazy!

Why the Dictionary?

GenAI is a liminal space. It's changing rapidly. As a result, new terms are being added continiously.

The Problem

Understanding new AI "buzzwords" is not always an easy task. Definitions can be too abstract and fail to describe how these terms are actually being used.

Example of the Problem

What is an AI agent?

When we use the term 'agent', we typically refer to apps like customer-service chatbots or coding agent.

IBM defines it as:

a system that autonomously performs tasks by designing workflows with available tools."

The issues with this definition are:

• The word "system" is too generic. Agents usually refer to an app.

• Agents are not always autonomous; human-in-the-loop and user-feedback are popular ways of ensuring agents are safely executing tasks.

• Agents don't always design workflows. Some apps use orchestration graphs to make LLM models perform single, specific tasks. Even when agents design workflows, it might be a sub-flow within a larger, developer-designed workflow.

• The pharse "with available tools" is too technical relative to the rest of the definition. Someone who doesn't know what an 'agent' is will probably not understand that 'tools' refers to programming functions that provide additional context or computations.

Overall, the definition doesn't provide you with a concrete picture of what an agent is.

A Solution

A dictionary that simply and concretely defines AI terms. To do so, the dictionary will do the following:

1. Provide a 'term type' for each term. Similar to word types in traditional dictionaries, 'term type' will describe what the term refers to. Examples include: architecture, document format, protocol, and behaviour.

2. Provide 'related terms' for each term. This is also similar to conjugations/derivations in traditional dictionaries, and it helps route users to the root term. For example, some of the related terms to 'agent' are agents and agentic.

3. A simple, concrete definition that defines terms as they're commonly used. To do so, the dictionary will provide users with different definitions depending on their background.

   • First, there will be a general defintion that should be understood by the average Joe Shmoe. Joe Shmoe is a middle-aged chef, knows a few things about AI and where it's used. He uses ChatGPT from time to time, but he won't know about specific technologies like 'agents' or apps like Notebook LM.

   • Furthermore, there should also be an 'original' definition, as in a definition that is similar to how the term is popularly defined. In the aforementioned example, that would be the IBM definition. The 'original' definition should preferably be quoted, with a corresponding source. This 'original' definition will help provide users with context on how the term is commonly defined and understood. This will help ensure they're not isolated or misunderstood when engaging in conversations relating to the term.

   • There should also be a software definition that should be understood by the average Alex Dev. Alex is a middle-aged full-stack developer who makes websites for an agency. She extensively uses Claude Code, and she's heard of terms like 'agents' and 'MCP'. But, she doesn't really know how they work or how they fit into her development tasks.

4. The dictionary should also have an example. That's one or two lines that help explain what the term refers to.

5. A diagram! A picture is worth a thousand words, and this dictionary is planning on using diagrams to convey the various elements associated with a term.

Example of the Solution

Agent

Term Type: Architecture

Related Terms: Agents, Agentic

Concrete Definition

An AI-model that uses additional, external data to generate a response.

8G Mobile uses an agent in the form of a customer serivce chatbot. When a user asks about their bill, the chatbot retrieves their records to tell them how much they owe.

flowchart
    model@{shape: rounded, label: "AI Model"}
    data@{shape: rounded, label: "Data"}
        model --> |request|data
        data --> |receive|model
    model --> Goal@{shape: rounded, label: "Response"}

Loading

Original Definition

"... a system that autonomously performs tasks by designing workflows with available tools." (IBM, 2024).

Software Data

Attaching context data and tools (programming functions) to LLM calls.

You can create an agent by attaching a 'GetWeather' tool to LLM calls. When a user asks about the weather, the LLM will call your 'GetWeather' tool to provide the user with the requested weather conditions.

Contributions

This project is open to contributions! A CONTRIBUTING.md is planned to be added soon to detail how you can easily contribute to this project.