Summary Ai

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:
AI assistants can speed up drafting and analysis, but outputs need human review and quality checks.

{
  "expected_contains": [
    "speed",
    "human review",
    "quality"
  ]
}