Skip to main content
Projects overview pageProjects overview page

Projects overview with the Example Project and kickoff banner.

Kick off your first run in minutes using the Example Project that’s created automatically when you sign up. You can also browse the run that was kicked off for you and explore how testsets, prompts, and metrics fit together.
1

Find the Example Project and open Kickoff Run

On the Projects overview page, you’ll see a banner welcoming you and a card for the Example Project. Click the banner’s button or the project card’s “Kickoff run” — this opens a pre‑filled Kickoff Run modal like the one below.
Kickoff modal with prefilled selectionsKickoff modal with prefilled selections

Kickoff Run modal pre‑filled with a Testset, Prompt, and Metrics.

2

Kick off your first run

The modal is pre‑filled with a Testset, Prompt, and Metrics using Scorecard Cloud. You can change selections or keep defaults.
Kickoff modal testset pickerKickoff modal testset picker

Pick a Testset (pre‑selected).

Next, choose one or more Metrics, or pick a Metric Group for consistency.
Kickoff modal metric selectorKickoff modal metric selector

Optionally select multiple metrics or a metric group.

Click “Kickoff run”. A toast confirms creation and links directly to results.
Success toast with link to runSuccess toast with link to run

Run created — follow the link to results.

3

View results (or open the sample run)

After your run starts and scoring completes, open the results to see per‑record scores, distributions, and explanations. You can also click “Run again” to rerun with new settings.
Run details pageRun details page

Run details with scores and aggregates.

Tip: Click Run Again to iterate with a different prompt version, model, or metric set.
Run Again button on run detailsRun Again button on run details

Run Again lets you quickly iterate.

Prefer to just explore? Visit Runs & Results to open the example run that was created for you automatically.
Runs list with example runRuns list with example run

Runs list with your first example run.

4

Browse the Example Project

Learn how the sample data is organized:
  • Emoji Testset: inputs userQuery → expected ideal (emojis).
  • Tone Testset: inputs original, tone → expected idealRewritten.
  • Prompt versions for Emoji and Tone — already set to Scorecard Cloud with low temperature for consistency.
  • Metrics: Correctness (AI, 1–5), Emoji Format (AI, Boolean), Human Emoji Preference (Human, 1–5), Human Tone Check (Human, Boolean).
  • Metric Group: Emoji Metrics = Emoji Format + Human Emoji Preference.
Testsets overviewTestsets overview

Testsets overview.

Open a Testset to see its schema and Testcases. Click a testcase row to view its inputs and expected outputs.
Testset detailsTestset details

A sample Testset with Testcases.

Next, browse Prompts. Use “View” to open a prompt, review messages, and model settings.
Prompts listPrompts list

Prompts list.

Inside a prompt version, see the template (Jinja‑style variables) and evaluator model configuration.
Prompt version editorPrompt version editor

Prompt version with template and model settings.

Finally, explore Metrics to learn how scoring works. Each metric has guidelines, evaluation type, and output type.
Metrics listMetrics list

Metrics configured for the Example Project.

​
Where to go next

  • Read about creating and managing Testsets in Testsets
  • Dive deeper into running evaluations in Runs & Results
  • Explore interactive prompt iteration in the Playground
  • Define and reuse evaluation criteria with Metrics
That’s it — you’ve seen Scorecard in action and how example data flows through prompts, runs, and metrics. Have fun iterating!