Reply to today's customer messages
Copy-pasting the same reply 60 times, changing only 'Sir' to 'Ma'am'
Tested Claude Opus 5.5, medium effort · 15 Nov 2026 · on the example values
Collect today's messages
Use ticket codes, questions and verified order facts. Remove personal details; copy approved FAQ answers.
Privacy Remove customer phone numbers, addresses, order payment details and personal identifiers. Use ticket or order refs instead.
Whenever I send questions, draft replies. FAQ: [Approved FAQ]. Questions: [Customer questions]. Sign off: [Sign off]. A. One short (up to 6 lines) reply per ticket, using only approved answers. B. Table: ticket, answered or needs check, missing fact. C. Internal follow-up list. Unknown order status goes to dispatch, no delivery promise. Use only supplied facts and policy. No admission of legal liability, refund or replacement promise unless the supplied policy permits it and an authorised person confirms. No invented dates, prices or outcomes. A person checks before sending or deciding. Line limits count body lines only, not subject, greeting or sign-off. Keep every required fact; if they do not fit, say so instead of dropping one.
Set it up once. Save the approved rules and output format, not customer details. Pick your tool at the top to see how.
What is that?
A Project is a folder in ChatGPT that keeps your instructions and files for every chat inside it. It's on the free plan too. Checked 14 Nov 2026.
What is that?
A Project in Claude is a workspace with its own instructions and files that every chat inside it uses. Checked 14 Nov 2026.
What is that?
A Gem is a custom Gemini that loads your instructions before every chat. Free on every plan; you create it on a computer. Checked 14 Nov 2026.
What is that?
Signed in with a work account, Microsoft's Copilot Chat applies enterprise data protection: your prompts aren't used to train its models. Checked 14 Nov 2026.
After that, each time: send the next masked notes or export and current rules; check the result.
First time? Try it in a normal chat: paste and send.
Which model? The free one in any tool is fine.
In your AI tool: paste, send.
- T1Office hours. Use supplied hours.
- T2Catalogue. Offer approved catalogue; attach locally.
- T3Status unknown. Check dispatch, no date promise.
Then send this: Match each reply to its ticket and FAQ. Count answered and pending.
It guesses delivery
Reply: "Status unknown; ask dispatch."
It adds refund
Reply: "No refund promise."
Too robotic
Reply: "Use simple WhatsApp English."
Sir ne bola urgent. Ab bolo: ho gaya.
Did it work?
If your whole team does this, we'll set it up for all of them in one session.