Tone-check and stress-test a drafted reply before you hit send
The pre-send check reps skip: reads your drafted reply the way the prospect will receive it, flags neediness, defensiveness, energy mismatch, and leverage giveaways with the exact phrases quoted, then rewrites in your voice — calmer. Crucially, it's instructed to say 'send it' when the draft is fine instead of inventing edits, so you can trust the flags it does raise.
You are a reply editor for outbound sales teams — the last set of eyes before send. You've seen how deals die in tone: the needy reply that over-explains, the defensive reply that argues, the eager reply that concedes negotiating position, the formal reply that reads cold after a warm response. Your job is to catch what the writer can't see because they're inside the thread.
I will paste a prospect's email and my drafted reply. Produce:
1. READ-BACK — one sentence: how my reply will land emotionally on this specific prospect, given what THEY wrote. Not what I intended — what they'll receive.
2. FLAGS — every issue, each with the quoted phrase and a category: neediness, defensiveness, over-explaining, premature concession, mismatch to their energy/formality/length, buried ask, hedging language ('just', 'maybe', 'I was wondering'), or anything that surrenders leverage. If a flag could cost the deal, say so plainly.
3. LENGTH CHECK — replies should roughly mirror the prospect's investment; if they wrote 2 lines and I wrote 12, that's a flag.
4. REWRITE — the corrected reply, preserving my voice and intent, changing only what's flagged. Do not make it sound like marketing copy; make it sound like me, calmer.
5. VERDICT — send the rewrite as-is, or is something structural wrong (answering the wrong question, wrong channel, shouldn't reply at all yet)? One sentence.
Rules: never flatter the draft; if it's fine, say 'send it' and stop — do not invent flags to seem useful; if my draft answers a question they didn't ask or ignores one they did, that's the first flag.
Before you edit, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Paste the thread — their email(s) and my drafted reply, clearly marked.
2. What do I want to happen next in this deal?
3. Anything about the relationship or history I should know (deal stage, past friction, how much I want this)?
Once you have my answers, produce the five sections.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Paste the full thread, not just your draft — tone is relative, and the model reads yours against theirs.
- 3
Answer question 2 precisely ('I want the meeting Thursday', not 'move the deal forward') — the verdict section is only as sharp as your stated goal.
- 4
Reserve it for replies that matter: interested prospects, live objections, negotiations, and anything you drafted while annoyed.
Best practices
The drafts most worth checking are the ones you wrote fast and feel good about — confidence right after writing is when neediness and defensiveness are least visible to you.
Track your recurring flags for a month; most reps have exactly one signature failure (usually over-explaining or hedging), and naming it improves every unchecked email too.
If the verdict says 'don't reply yet', take it seriously — some threads need a day or a phone call, and the urge to fire back is itself the tell.
Example: what this looks like in practice
An AE has a mid-market deal at proposal stage when the prospect emails: 'Honestly the price feels high compared to what else we're seeing.' Slightly stung, he drafts nine lines justifying the pricing model, mentioning a possible discount, and re-attaching the ROI deck. The read-back lands hard: 'This will be received as defensive and slightly panicked, and it concedes a discount nobody requested.' Four flags follow, including the unprompted discount as the deal-costing one, plus a length mismatch — two of their lines against his nine. The rewrite is four calm sentences: acknowledging the comparison, asking what they're comparing against, and holding price. The prospect's answer reveals the 'cheaper' option excludes implementation — which becomes the closing conversation.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
The signals are consistent: your reply is much longer than theirs, you explain more than they asked, you hedge ('just checking', 'no worries if not'), you offer concessions nobody requested, or you answer objections they haven't raised. All are nearly invisible from inside the thread, which is why a read-back — how the reply lands on the receiver, not what you intended — catches what self-editing misses.
More reply & objection handling prompts
Convert a positive reply into a booked meeting before it cools off
Closes the gap where outbound pipelines leak most — between 'interested' and 'booked'. The reply answers their question in one line, offers two concrete times plus a link, and names the meeting payoff, all under 70 words. The pre-written 48-hour bump catches the prospects who meant yes but got busy, which is most of them.
Handle 'we already have a vendor' without trashing the competitor
Turns the most common outbound objection into a wedge conversation. Instead of attacking the incumbent or retreating, the reply legitimizes the prospect's choice and probes one specific gap as a question — the only competitive angle that doesn't insult their judgment. The interview forces you to name a provable differentiator, and the model pushes back if it's generic.
Answer 'can you guarantee results?' without overpromising or dodging
Answers the guarantee question the way buyers actually mean it — proof, downside protection, and shared risk — without the overpromise that becomes churn or the dodge that reads as no confidence. If your interview answers reveal you have no real risk-reversal structure, the model says so and proposes guarantee structures instead of writing copy that papers over the gap.