Prompt Studio

Test and iterate on prompts in real-time

The Prompt Studio is an interactive environment for testing and iterating on your prompts before using them in production.

Accessing the Studio

Access the Studio from multiple places:

1. From the Dashboard: Click Studio in the sidebar
2. From a Task: Click the Studio button in the task header
3. From a Prompt: Click Open in Studio on any prompt

Studio Interface

Header Controls

The header contains:

Control	Description
Prompt Selector	Choose which prompt to test
Go to	Navigate to the prompt’s detail page
Branch Selector	Choose which branch to use
Commit Selector	Test specific versions
Model Settings	Configure provider, model, temperature
Execute	Run the prompt

Prompt Template Panel

The main editing area shows all messages in your prompt:

• System messages (blue background)
• User messages (gray background)
• Assistant messages (white background)

Edit messages directly in the Studio—changes auto-save to your working state.

Variables Panel

On the right side, you’ll see input variables:

• Each variable from your prompt’s input schema appears here
• Fill in values to test different scenarios
• Supports text, objects, arrays, and media types

Testing Prompts

Basic Testing

1. Select a prompt

   Use the prompt selector dropdown to choose a prompt.

2. Fill in variables

   Enter values for each input variable.

3. Configure model settings

   Choose provider, model, temperature, and max tokens.

4. Click Execute

   Run the prompt and see the response.

Variable Types

Type	How to Enter
String	Plain text in the input field
Number	Numeric value
Boolean	Toggle switch
Object	JSON in code editor
Array	JSON array in code editor
Image	Upload or paste URL
File	Upload file

Viewing Results

After execution, you’ll see:

• Response content: The LLM’s output
• Token usage: Input and output token counts
• Latency: Time to generate response
• Cost estimate: Based on model pricing

Results are automatically logged for observability (visible in the Traces tab).

Import from Logs

Replay previous executions by importing variable values from traces:

1. Click Import from Logs

   Open the import dialog.

2. Select a trace

   Browse recent traces or search by metadata.

3. Import

   Variable values are populated from that execution.

4. Modify and re-run

   Tweak values and execute again to compare.

This is useful for:

• Debugging production issues
• Testing edge cases from real data
• Building test cases from actual usage

Test Cases

Create and manage test cases for systematic testing:

Creating Test Cases

1. Set up variables

   Fill in variable values for a test scenario.

2. Click Save as Test Case

   Name your test case (e.g., “Password reset request”).

3. Add expected behavior

   Optionally add notes about expected output.

Running Test Cases

1. Click Test Cases to see saved cases
2. Select one to load its variable values
3. Execute and compare results
4. Create observations for regression testing

Multi-Turn Conversations

Test conversational prompts with multiple turns:

1. Execute initial prompt

   Run with user’s first message.

2. Click Add Turn

   Add the assistant response and a new user message.

3. Execute again

   Continue the conversation.

Useful for testing:

• Follow-up question handling
• Context retention
• Conversation flow

Tool Calling

Test prompts with tools (function calling):

1. Configure tools: Attach schemas to your prompt
2. Execute: The model may return tool calls
3. Provide results: Enter mock tool results
4. Continue: See how the model uses the results

Best Practices

Test edge cases

Try empty inputs, very long inputs, and unusual characters.

Compare models

Test the same prompt with different models to compare quality and cost.

Save test cases

Build a library of test cases for regression testing.

Test before committing

Always test prompt changes in Studio before committing.

Use real data

Import from logs to test with production-like inputs.

Next Steps

Creating Tasks & Prompts

Create content to test

Variables & Properties

Define input variables

Reviewing Telemetry

Analyze test results

Branching & Committing

Save tested changes