Generation
Harness the power of AI
What does it do?
Generations give you access to dozens of different AI models. They can help you write, design, and even code. You can use them to generate text, analyze images, and much more. You’ll probably want at least one generation in every WordApp, and the more you use them, the more powerful your WordApps become.
How do I use it?
A generation takes all the data that’s appeared in the WordApp so far and passes it to your AI model of choice. The model then generates new content based on what it’s seen.
To create a generation, type /generation in the editor, and hit Enter. You’ll be prompted to fill in some details
about the generation, like its name and the model you want to use, further explained below. Once you run the WordApp,
the model will be fed all the content above the generation and generate new content based on it, which you can then
reference with a @mention.
Options
A number of options appear in the sidebar when you create a generation. Here’s what they mean:
Name
The name of the generation. You’ll need this later if you want to @mention the output of the generation.
Creativity
How creative the generation should be. A higher creativity level will produce more varied and interesting results, but is more likely to result in unexpected outputs.
As a rule of thumb, increase the creativity level if you’re getting overly consistent or boring outputs, and decrease it if the outputs are too chaotic or nonsensical. Creative works like poetry or fiction often benefit from higher creativity, while logical or technical works like code or reports often benefit from lower creativity.
Generation type
When the model should stop generating. AI models are quite content to talk until their context window runs out, so you’ll typically want to set a generation type to tell the model when to stop.
Options include:
| Generation type | How it works |
|---|---|
| Short | Stops generation after the first word or symbol |
| Sentence | Stops generation at the end of the first sentence |
| Full | Lets the model choose when to stop |
| Custom | Stops at the first instance of the text of your choice. You can choose up to four options |
We recommend starting with Full and only switching to Short or Sentence if you’re getting overly long outputs.
The worst case scenario from this approach is you get too much text your next generation needs to deal with, but most
models are quite good at knowing what to pay attention to.
Model
Which AI model you’d like to use. You can choose from a variety of models, each with its own strengths and weaknesses.
Here’s a video where we go through some of the different model choices you can make.
See our dedicated model documentation for our full list of supported models and their capabilities.
Outputs
Generations produce a single output, the content generated by the model. You can reference this output in the editor with a @mention using the name of the generation specified in the generation’s settings.