Library › Cybersecurity AI › Managers and team leads
Answer an employee's worried question about a breach rumor
- For Managers and team leads
- You practice Keeping the AI to your sources
- Time about 5 minutes
About this exercise
An employee DMs you: 'I heard we got hacked, is my data out there?' Reply using only the official security note. Exactly 3 lines starting 'Short answer:', 'What happened:' and 'What to do:'. Don't repeat rumors or guess beyond the note. Calm, plain words. Plain text, under 70 words.
Common mistakes when you ask AI for this
- Hedging. The AI says 'it's possible' and suggests freezing credit to be safe, which feeds the rumor. Try: Say: "Use only the official note. It says no employee data was accessed."
- Naming the person. The AI mentions the marketing coordinator in a way that identifies them. Try: Add: "Don't identify whose account it was."
- No clear answer first. The AI explains the incident before answering Theo's question. Try: Ask: "First line: Short answer: yes or no."
- Trusting the AI to count words. AI is bad at counting. Ask for "under 70 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 55 words total."
- Letting markdown in. AI adds bold and headings by default, and in a chat DM they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."
What a strong prompt includes
- Uses only the official note
- Gives the 3 line labels
- Sets a calm tone
- Sets a word limit
- Asks for plain text
Related exercises
- Accept a job offer and confirm the exact terms (Writing AI · Job seekers)
- Allocate shared rent by headcount using the right roster (Finance AI · Accountants)
- Announce a seasonal offer with its real terms and no fake scarcity (Sales AI · Small business owners)
- Answer a 'where is my order' email with the real new date (Writing AI · Customer support teams)
- Answer a big discount ask with two priced options (Writing AI · Sales and customer success)