Library › AI Evals › Business analysts

Decide whether tonight's eval score should trigger an alert

  • For Business analysts
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Advanced

About this exercise

You are on the analytics team watching Pedalbot's nightly refund-accuracy score. Apply the alert rule in the material to the last 7 nights and tonight's score, and show the math. Write plain text, exactly 6 lines labeled Average, Gaps squared, Standard deviation, Alert line, Tonight, Decision, each in the form 'Label: working = result' (for example 'Average: sum / 7 = result'). The Gaps squared line lists the squared gap for each night in the order given, then the total. Under 90 words.

Common mistakes when you ask AI for this

  • Alerting on the lowest score. The AI sees the week's lowest score and says to alert. Try: Say: "Alert only if MORE than 2 standard deviations below, so exactly 2 is not an alert."
  • Skipping the working. The AI jumps to a verdict with no numbers. Try: Add: "Show Average, Gaps squared, Standard deviation and Alert line."
  • Using the wrong divisor. The AI divides by 6 or includes tonight in the average. Try: Add: "Use the previous 7 nights only, divide by 7."
  • Extra commentary. The AI adds bold headings and advice about the trend. Try: Add: "Plain text, exactly 6 labeled lines, nothing else."

What a strong prompt includes

  • Uses the 7 previous nights
  • Shows each step
  • Divides by 7
  • Fixes the line labels
  • Asks for plain text

Practice this now ↑

Related exercises