User Guide
- Manage Prompts
- Create Prompt
- Edit Version
- Generate Version
- Rename Version
- Delete Version
- Set Primary Version
- Compare Versions
- Token Count and Cost
- Update Prompt Use Case
- Copy Prompt to Workspace
- Move Prompt to Workspace
- Optimize Prompts
- Prompt Scoring
- Scoring Criteria
- Prompt Risk
- Prompt Balance
- Prompt Heatmap
- Connect AI Providers
- AI21 Labs
- Amazon Bedrock
- Anthropic
- Azure OpenAI
- Azure Serverless
- Cohere
- Deep Infra
- Fireworks AI
- Google Gemini
- Groq
- Hugging Face
- Hyperbolic
- Lambda
- Meta
- Mistral
- Moonshot AI
- OpenAI
- Perplexity
- Together AI
- xAI
Generate Version
On this page you'll find the following:
Get Started
You can save yourself from having to manually create new prompt versions from scratch by generating verions based on the prompt use case.
To do this, go to the version's Generate tab. The Use case field will be prepopulated, which you can modify if needed. You can also optionally select criteria from the dropdown list. Then click the purple Generate prompt button.
Tip: Selecting custom criteria helps generate an even stronger prompt compared with just relying on the use case.
The generated prompt will start to stream in the PROMPT box on the right, and you'll see a Generating prompt... spinner below.
The prompt stream will complete after a few seconds, at which point the Generating prompt... spinner will be replaced with a green Save prompt as new version button. You'll also see the number of tokens used to generate the prompt and how long it took.
If you like the generated prompt, you can click the green Save prompt as new version button to save the version with the generated content. You can also click the purple Generate prompt button again to regenerate a similar yet different prompt, giving you options to choose from.
Generate Version with Different Models
To change which AI model is used to generate the version, click the Settings link near the top-right of the page.
This will open a side panel where you can select different models and change the temperature setting. Make your model selection, click the green Apply button, then generate the prompt version.
Tip: Changing the temperature allows you to control how creative the prompt generation will be based on the given use case. Values closer to 0 will be less creative while values closer to 1 will be more creative.
