​
In this quickstart we will create a prompt for classifying online reviews of movies as either positive or negative.

​
1. Create Your First Prompt

You will see the Prompt Development Dashboard.

​
2. Define the Prompt

In the left panel of the dashboard, you can define the messages that make up the prompt.

​
Step 1: system message

Define the LLM’s role and instructions. Specify the expected output format to make the response machine-readable.

You are a sentiment classifier.
Classify the following movie review as 'positive' or 'negative'.

Respond in JSON format:
{"sentiment": "<result>"}

​
Step 2: user message

Write a template for the user input using a placeholder for the review text.

Templates use Mustache syntax — wrap parameter names in double curly braces ({{ }}).

Review: {{review}}

​
3. Configure the Prompt

In the right-side panel, go to the Config tab. Here you’ll configure how the LLM runs and define the inputs and outputs.

​
Step 1: Model Configuration

  • Select a model (e.g., gpt-4, claude, etc.)
  • Set temperature to 0 for consistent deterministic outputs
  • Ensure response format is set to JSON

​
Step 2: Define Prompt Parameters

  • Add a parameter named review
  • Set its type to text to allow multi-line input
  • This corresponds to the {{review}} placeholder in your prompt

​
Step 3: Define the Output Schema

  • Add a result field named sentiment
  • This matches the key in the expected LLM JSON response
  • Used for validation and test automation

​
Step 4: Try a Negative Input

You can try this input in the playground later:

{
  "review": "The plot was confusing, the pacing was terrible, and the acting was wooden."
}

​
4. Run Prompt in Playground

On the right-side panel, switch to the Playground tab.

Here you can run the prompt manually, inspect the LLM response, and make prompt edits.

​
Step 1: Add Sample Input

Provide a sample value for the review parameter. For example:

Positive review

{
  "review": "A visually stunning masterpiece with a moving story and brilliant acting."
}

​
Step 2: Run and Inspect

  • Click Submit
  • Review the output JSON response
  • Iterate on prompt instructions if necessary for better accuracy

​
Step 3: Repeat with Another Input

Try different inputs to validate how well the prompt handles variations.

​
5. Add a Test Case

On the right-side panel, switch to the Test Cases tab.

Test Cases allow you to define fixed inputs and expected outputs that can be validated automatically. This is useful for regression testing and prompt versioning.

​
Step 1: Add Test Case

  • Click Add Case
  • Fill the name: positive 1
  • For parameter values, set review to:
A visually stunning masterpiece with a moving story and brilliant acting.
  • Click Save

​
Step 2: Add Assertion

  • After saving the test case, click Add Assertion
  • Select  property   sentiment as the output field to check
  • Set the operation  to equal
  • Set Expected   text output to  positive
  • Save the assertion

You now have a fully defined test case that will automatically validate that the prompt produces the expected output for the given input.

Repeat the steps to add a negative test case as well.

​
6. Run Test Cases

On the right-side panel, switch to the Test Runner tab to validate your prompt automatically using the test cases you’ve defined.

​
Step 1: Run All Tests

Click the Run All button to execute all your test cases.

Each test case will run the LLM with the given input and compare the output against the expected assertion(s).

​
Step 2: Set API Key (if required)

If this is your first time running tests or if the API key is missing/expired:

  • You’ll be prompted to set the API key for your LLM provider (e.g., OpenAI, Anthropic)
  • You can find this in the Settings panel if you need to update it later

​
Step 3: Review Results

  • The test run session will show the pass/fail status of each test
  • For failures, you can click to inspect the actual vs expected outputs
  • Use this feedback to iterate on your prompt or test assertions

​
7. Next Steps

You now have a working prompt with automated test coverage! Here’s what you can do next:

​
🔁 Iterate and Expand

  • Try your prompt with different models or settings (e.g., temperature, top-p)
  • Add more test cases to cover edge cases and ensure consistency
  • Modify the prompt instructions to improve classification accuracy

​
🧪 Strengthen Test Coverage

  • Add negative cases, ambiguous inputs, or malformed reviews
  • Explore different assertion types beyond equal — e.g., contains, regex, in list

​
🚀 Deploy and Integrate

  • Learn how to version your prompts to track improvements over time
  • Explore deployment options to integrate your prompts via API or SDK
  • Use environments to manage separate dev/staging/prod configurations

​
8. Dive Deeper

  • Learn about prompt versioning
  • Learn about deployment options to integrate the prompts in your system
  • Learn more about test cases and assertion types