Skip to main content

​
1. Sign up

If you don’t have an Adaline account yet, you can create one by signing up at app.adaline.ai. After creating an account, you will notice the following:
  • A Shared teamspace containing workspace-wide public projects and other entities.
  • A Private teamspace with a sample project, prompt and dataset.

​
2. Setup an AI provider

1
Navigate to the workspace settings from the sidebarClick on settings
2
Click on the Providers buttonClick on the 'Providers' button
3
Configure your AI provider by giving it a name and adding its credentialsConfigure your AI provider

​
3. Import the sample project

To get started quickly, we have prepared a sample project that includes a pre-configured prompt, dataset, and evaluators. Import it into your workspace by following these steps:
1
Download the sample project JSON file from here
2
In the sidebar, click on the Import project button and choose the JSON file you just downloaded.Click import project
3
Once the import completes, verify that the project now contains the sample prompt, dataset, and evaluators. You should see all three listed in the sidebar.Imported project

​
4. Explore the Evaluators

Evaluators are the scoring functions that assess your prompt’s output. Each evaluator measures a different dimension of quality, giving you a quantified view of how your prompt is performing. Navigate to the Evaluate tab within your prompt. You will see a list of evaluators that were included in the sample project. View evaluators

​
5. Explore the Dataset

A dataset is a collection of test cases. Each row in the dataset represents one test case, and each column maps to a variable in your prompt or evaluator. Click on the sample Dataset in the sidebar. View dataset Inspect the rows and columns. Notice how the column names correspond to the variable placeholders in the prompt — these values will be substituted into the prompt at runtime for each test case. There is also an extra column called expected which is used to store the expected output for the evaluator to compare against, not directly used in the prompt.

​
6. Run your Evaluation

Now that you understand the building blocks — a prompt, a dataset, and evaluators — here is how they all come together when you run an evaluation.
1
Open the Evaluate tab within your prompt and click Evaluate.Run evaluation
2
When an evaluation runs, Adaline takes each row in your dataset and uses it as a test case:
  1. The variable values from the row are substituted into the prompt’s placeholders.
  2. The prompt is sent to the configured model, and the model generates a response.
  3. The response is then passed through every evaluator attached to the prompt.
  4. Each evaluator produces a quantified score for that test case.
This process repeats for every row in the dataset, giving you a complete matrix of scores across all test cases and evaluators.
3
Once the run completes, review the results table. Each row shows the test case inputs, the model’s output, and the score from each evaluator.View evaluation resultsUse these results to compare prompt quality and performance over time. As you iterate on your prompt — adjusting instructions, switching models, or tuning parameters — re-running evaluations gives you an objective, quantified measure of whether your changes are improving or degrading output quality.
Congratulations! You just ran your first evaluation in Adaline. Read more about evaluation strategies