Library › Customer Support & Success AI › Customer support teams
Reply to an angry public post without sharing details
- For Customer support teams
- You practice Getting the tone right
- Time about 5 minutes
- Level Beginner
About this exercise
Reply publicly to the post as Brightly Support. Start with exactly "@mike_t". Plain text, under 30 words. Apologize once, invite him to DM us, and share no order details. Do not argue. End with exactly "^Sam".
Common mistakes when you ask AI for this
- Explaining the real reason. The lookup shows what happened and the AI shares it publicly. Try: Say: "Share no order details or reasons; ask for a DM."
- Blaming the customer. The teammate suggests saying it's his fault. Try: Add: "Do not argue or blame."
- Answering the complaint in public. The AI explains and apologizes at length without inviting a DM. Try: Say: "Apologize once and invite him to DM. End with exactly ^Sam."
- Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands well over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
- Getting markdown back. AI adds bold or hashtags. Try: Say "plain text, no hashtags".
What a strong prompt includes
- Asks for plain text
- Sets a length limit
- Asks for a DM
- Bans details
Related exercises
- Acknowledge a director's critical feedback without defensiveness (Leadership AI · Executives)
- Acknowledge an accessibility bug without a promised date (Customer Support & Success AI · Customer support teams)
- Acknowledge an executive escalation within the hour (Customer Support & Success AI · Executives)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
- Announce a CFO departure in three plain sentences (Leadership AI · Executives)