Prompt Lifecycle
Prompt Library supports the complete lifecycle of a prompt, from creation to activation. A typical prompt lifecycle includes:Test and Compare
Test the prompt across one or more models and compare responses, token usage, and response times.
Create and Manage Prompts
The Prompt Library page displays all prompts available in the selected project. Prompt Library allows you to create and maintain reusable prompt templates. For each prompt, you can:- Define prompt instructions and content.
- Add tags for categorization.
- Save prompts as drafts.
- Promote validated prompts to the active version.

Manage Prompt Versions
Prompt Library maintains versions of each prompt template. Each prompt can have multiple versions. The Versions tab allows you to:- View available prompt versions.
- Track prompt revisions over time.
- Compare changes between versions.
- Promote a selected version to active status.
Prompt States
| State | Description |
|---|---|
| Draft | A work-in-progress version used for editing and testing. |
| Active | The published version intended for production use. |
Test and Compare Prompts
Use Test & Compare to evaluate prompt behavior across multiple language models. Testing prompts before deployment helps identify the most effective model and prompt combination for your use case. When testing a prompt, you can:- Select a prompt version.
- Choose models for comparison.
- Provide a test user message.
- Upload an optional context file.
- Execute the prompt against the selected models simultaneously.

Use Context During Testing
Prompt tests can include additional context through uploaded files. Uploaded files are made available during prompt execution and can be used to evaluate how the prompt behaves when supplied with supporting information. This helps validate prompts against realistic scenarios and project-specific content.View Prompt References
The References tab shows where a prompt is used within the project. Use References to:- Understand prompt dependencies.
- Assess the impact of prompt changes.
- Identify agents and workflows that rely on the prompt.
Best Practices
- Use descriptive names that clearly indicate a prompt’s purpose.
- Add tags to improve organization and searchability.
- Save changes as drafts while iterating on prompts.
- Test prompts across multiple models before promoting them to active status.
- Review prompt references before modifying active prompts.
- Use version history to track prompt evolution and maintain previous revisions.