{
  "name": "maintainer-clarity-smoke",
  "systemPrompt": "Answer concisely and explicitly. No fluff.",
  "cases": [
    {
      "id": "fixed-task-set-definition",
      "input": "In one sentence, define what a fixed task set means for eval workflows.",
      "expectContains": ["same tasks"]
    },
    {
      "id": "extension-gaps",
      "input": "Name two extension-level gaps that can affect reproducible eval workflows in pi.",
      "expectContains": ["trace", "reproducibility"]
    },
    {
      "id": "do-not-overclaim",
      "input": "Should this be pitched as a huge replacement right away? Answer yes or no and one short reason.",
      "expectContains": ["no"],
      "expectNotContains": ["huge replacement"]
    }
  ]
}