You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+26-61Lines changed: 26 additions & 61 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,80 +10,45 @@ GenAI is a liminal space. It's changing rapidly. As a result, new terms are bein
10
10
11
11
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.
12
12
13
-
#### Example of the Problem
13
+
###The Solution
14
14
15
-
_What is an AI agent?_
15
+
A simple, straightforwad, community-driven dictionary that puts a real definition to AI buzzwords.
16
16
17
-
When we use the term 'agent', we typically refer to apps like customer-service chatbots or coding agent.
17
+
Additionally, it provides 2 levels of definitions:
18
18
19
-
IBM defines it as:
19
+
- A **general** definition suitable for everybody!
20
+
- A **software** definition suitable for software folks (and others familiar with the AI space).
20
21
21
-
> a system that autonomously performs tasks by designing workflows with available tools."
22
+
---
22
23
23
-
The issues with this definition are:
24
+
## Contribute!
24
25
25
-
- The word "system" is too generic. Agents usually refer to an app.
26
+
There's a variety of ways you can contribute to the dictionary!
26
27
27
-
- Agents are not always autonomous; human-in-the-loop and user-feedback are popular ways of ensuring agents are safely executing tasks.
28
+
### Word of the Day
28
29
29
-
- 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.
30
+
If you want to suggest a word of the day, simply open up a pull request with an edit to: `lib/term_of_the_day.ts`!
30
31
31
-
- 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.
32
+
### Add a New Term
32
33
33
-
Overall, the definition doesn't provide you with a concrete picture of what an agent is.
34
+
If you want to add a new term to the dictionary, open up an issue with the term in the title, and your suggested "General" and "Software" definition in the body of the issue.
34
35
35
-
### A Solution
36
+
Example Issue:
36
37
37
-
A dictionary that simply and concretely defines AI terms. To do so, the dictionary will do the following:
38
-
39
-
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.
40
-
41
-
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.
42
-
43
-
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.
44
-
- 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.
45
-
46
-
- 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](#example-of-the-problem), 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.
47
-
48
-
- 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.
49
-
50
-
4. The dictionary should also have an example. That's one or two lines that help explain what the term refers to.
51
-
52
-
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.
53
-
54
-
#### Example of the Solution
55
-
56
-
**Agent**
57
-
58
-
_Term Type_: Architecture
59
-
60
-
_Related Terms_: Agents, Agentic
61
-
62
-
##### Concrete Definition
63
-
64
-
An AI-model that uses additional, external data to generate a response.
65
-
66
-
> 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.
67
-
68
-
```mermaid
69
-
flowchart
70
-
model@{shape: rounded, label: "AI Model"}
71
-
data@{shape: rounded, label: "Data"}
72
-
model --> |request|data
73
-
data --> |receive|model
74
-
model --> Goal@{shape: rounded, label: "Response"}
38
+
```yml
39
+
----------------------------------------
40
+
| New Term: Vibe-coding |
41
+
|--------------------------------------|
42
+
| |
43
+
| General definition: .... |
44
+
| |
45
+
| Software definition: ... |
46
+
| |
47
+
|--------------------------------------|
75
48
```
76
49
77
-
##### Original Definition
78
-
79
-
"... a system that autonomously performs tasks by designing workflows with available tools." (IBM, 2024).
80
-
81
-
##### Software Data
82
-
83
-
Attaching context data and tools (programming functions) to LLM calls.
84
-
85
-
> 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.
50
+
This will help us open up the floor for discussion, before making a pull request.
86
51
87
-
##Contributions
52
+
### Other Stuff
88
53
89
-
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.
0 commit comments