[
  {
    "query": "How do we test this prompt change without shipping a quality regression?",
    "should_trigger": true
  },
  {
    "query": "Build an eval set and pass bar for our ticket-classification LLM",
    "should_trigger": true
  },
  {
    "query": "We want an LLM judge to grade helpfulness on our chatbot — how should we set that up?",
    "should_trigger": true
  },
  {
    "query": "Set up a regression gate before we keep iterating on our RAG prompts",
    "should_trigger": true
  },
  {
    "query": "Generate eval cases for this skilldrop SKILL.md so I can drop them in its evals folder",
    "should_trigger": false
  },
  {
    "query": "Summarize how much each team used AI tools last month from this telemetry",
    "should_trigger": false
  },
  {
    "query": "Compare Claude, GPT, and Gemini for our document-extraction use case and recommend one",
    "should_trigger": false
  },
  {
    "query": "What adoption and handle-time metrics should we track for the new AI feature?",
    "should_trigger": false
  }
]