fabric
is an open AI ecosystem that helps people integrate AI into their lives and work.fabric
helps people collect and integrate modular AI functionality, which we call _Patterns_, into various parts of their lives.
There are patterns for all sorts of life and work activities, including:
- Extracting the most interesting parts of YouTube videos and podcasts
- Summarizing opaque academic papers
- Creating perfectly matched AI art prompts for a piece of writing
- Rating the quality of content to see if you want to read/watch the whole thing
- Getting summaries of long, boring content
- Write a full essay in a particular voice, given an idea as input
- Create social media posts from any content input
- And a million more…
## Naming
`fabric` is themed off of, um…_fabric_. So, think blankets, quilts, patterns, etc. Here's the structure:
- The project itself is called **Fabric**, and it's the parent concept.
- Individual AI modules (think prompts) are called **Patterns**.
- Chaining together _Patterns_ to create advanced functionality is called a **Stitch**.
- The optional server-side functionality of `fabric` is called the **Mill**.
- The optional client-side scripts within `fabric` are called **Looms**.
## Structure
`fabric`'s main point is to make '**Patterns** available to everyone, but it also includes two other components that make it possible to _build your own Personal AI Ecosystem_.
_In other words you can have your own server, with your own copy of `fabric`, running your own specific combination of **Patterns** for your specific use cases._
Here are the three ecosystem pieces that work together.
- The **Mill** is the (optional) server that makes **Patterns** available.
- **Patterns** are the actual AI use cases.
- **Looms** are the modular, client-side apps that call a specific **Pattern\* hosted by a **Mill\*\*.
## Functionality
When you use `fabric`, it pulls the following content from the input.
- `IDEAS`
- Extracts the best ideas from the content, i.e., what you might have taken notes on if you were doing so manually.
- `QUOTES`
- Some of the best quotes from the content.
- `REFERENCES`
- External writing, art, and other content referenced positively during the content that might be worth following up on.
- `HABITS`
- Habits of the speakers that could be worth replicating.
- `RECOMMENDATIONS`
- A list of things that the content recommends Habits of the speakers.
## Usage
`extractwisdom` output can help you in multiple ways, including:
1. `Time Filtering`