Access Prompt Studio
- Log in and select Prompt Studio from the modules list.
- On the dashboard, view prompts in three tabs: All prompts, My prompts, Shared prompts.
- Click New prompt, enter a name, and click Proceed.
- Choose a creation method: Generate a prompt, Start from scratch, or Prompt library.
Create Prompts
Generate a Prompt
Expand a basic instruction into a detailed, comprehensive prompt using AI.- Click Generate a prompt.
- Select a model and enter your instruction.
- Review the AI-generated prompt.
- Click Proceed to copy it to the canvas for customization.
Only OpenAI and Anthropic models support prompt generation. You can also access this feature directly on the canvas via the Generate Prompt button.
Start from Scratch
Opens a blank canvas where you can manually write prompts, add variables, select models, and generate outputs with full control.Prompt Library
Access 65+ pre-built templates for common use cases like code generation, summarization, and Q&A.- Click Prompt library.
- Browse My templates (your saved templates) or All templates (built-in options).
- Select a template and click Use template to copy it to the canvas.
Templates are read-only. Edit only after copying to the canvas.
Use Prompt Canvas
Add Prompts
Supported JSON schema types: String, Boolean, Number, Integer, Object, Array, Enum, anyOf.
Add Variables
Variables let you test prompts with multiple values simultaneously. Syntax: Use{{variable_name}} in your prompt.
- Add variables in the Prompt field using double curly braces (for example,
{{product}}). - When variables are added, a Variables column appears.
- Assign values to each variable. Click Add an empty row for multiple test cases.
Select Models
Compare up to 5 models to identify the best fit for your use case.- Click the Select Model field.
- Choose a model and connection.
- Add additional models in columns to the right.
- Click the settings icon to adjust parameters (temperature, top k, top p, max tokens).
Generate Output
- Click Run to generate outputs.
- Review results in the model columns, including: response text, token count (input + output), and response time.
Maximum 10 rows can be generated simultaneously.