Summary Product

The model receives the prompt (and optional system message). The run uses scorer contains_any with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

Summarize in 2 short bullet points:
Product teams improve outcomes by running small experiments, measuring user behavior, and iterating weekly.

{
  "expected_contains": [
    "experiments",
    "measuring",
    "iterating"
  ]
}