Library › Data AI › HR and recruiting

Average interview panel scores after a recusal

Practice: Giving the right context. About 5 minutes.

About this exercise

You're the recruiter closing out a hiring panel. Ravi told you privately that he worked with Marco Ruiz before, so his score for Marco must be dropped (the scorecards don't show this). Write exactly 3 numbered lines, one per candidate, each showing the scores added and divided into an average (2 decimals), then one unnumbered last line: Advance: [name]. Plain text, under 70 words.

Common mistakes when you ask AI for this

  • Not telling the AI about the recusal. The scorecards don't show it, so the AI counts Ravi's 5 and Marco comes out on top. Try: Add: "Drop Ravi's score for Marco. Average Marco over 3 interviewers."
  • Not asking to see the work. Bare averages hide which scores were counted. Try: Add a line to copy: "1. Lena Cho: (3 + 4 + 4 + 3) ÷ 4 = 3.50"
  • Letting comments sway it. The AI weighs Ravi's 'culture fit' praise into the pick. Try: Add: "Pick on the averages only."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each line: "each line under 14 words."
  • Forgetting where it goes. AI loves markdown tables and bold, which show up as clutter in an applicant tracking system note. Try: Add: "Plain text, no bold, headings or tables."

What a strong prompt includes

  • Mentions the recusal
  • Asks to show the math
  • Asks for the pick last
  • Sets a word limit
  • Asks for plain text

Practice this now ↑

Related exercises