Library › Cybersecurity AI › Nurses and healthcare workers

Help the front desk spot a fake 'password expiring' email

  • For Nurses and healthcare workers
  • You practice Giving the right context
  • Time about 5 minutes

About this exercise

The front desk asks if this 'password expiring' email is real. Reply with a first line 'Not real: don't click', then exactly 3 numbered red flags quoting the email, then a last line starting 'Report:' with the clinic's steps. Plain text, under 80 words.

Common mistakes when you ask AI for this

  • No clear answer first. The AI explains before saying it's fake. Try: Ask: "First line: Not real: don't click."
  • Generic red flags. The AI lists 'urgency' without quoting the email. Try: Say: "Quote the email in each red flag."
  • Generic reporting. The AI says 'forward to IT' instead of the clinic's steps. Try: Add: "Report: the Report phishing button, then tell Grace."
  • Trusting the AI to count words. AI is bad at counting. Ask for "under 80 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 60 words total."
  • Too many red flags. The AI lists everything it can find. Try: Be exact: "Exactly 3 numbered red flags."
  • Letting markdown in. AI adds bold and headings by default, and in a chat reply they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

  • Puts the answer first
  • Asks for quotes
  • Uses the clinic's steps
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises