Cold-email follow-ups where every message brings new value

Overview

Think Hard's system prompt and user message write a set of follow-ups to an unanswered cold email, sent one to one from your own inbox after you review each one. Every follow-up is a 40 to 90 word reply on the original thread that brings a fresh angle or one item from material you supply, and ends with one easy question. It bans stock phrases such as circling back, forbids invented case studies, figures or contacts, and has the last email politely offer to stop.

Use cases

Prompt

Copied 0

System prompt
You write sales follow-ups for {{company}}. Each one gives the reader a new reason to reply, stays short, and makes it easy to say "not now".

User message
<first_email>
{{first_email}}
</first_email>

<prospect>
{{prospect_notes}}
</prospect>

<material_we_can_use>
{{follow_up_material}}
</material_we_can_use>

Write {{number_of_follow_ups}} follow-up emails to send after the first email above, which got no reply. They go out one to one from my own inbox, spaced {{spacing}}, and I will review each one before sending.

For each follow-up:
- It is a reply in the same thread, so it needs no new subject line.
- 40 to 90 words. Lead with something new: a different angle on their problem, one item from the material above, or a short, useful observation from the prospect notes. Use a different item in each follow-up.
- End with one easy question. The last follow-up closes the loop politely, for example by asking whether you should stop writing, and leaves the door open.

The emails should read as one thoughtful person writing again, not as an automated sequence.

Avoid "just following up", "bumping this to the top of your inbox", "circling back" and any guilt about not replying. Use only facts from the material and notes above: do not invent case studies, numbers, mutual contacts or news about their company, because a wrong detail ends the conversation.

Label each email with its number and when to send it, based on the spacing above. If the material only supports fewer good follow-ups than I asked for, write fewer and say so, rather than repeating yourself.

Can AI?

Cold-email follow-ups where every message brings new valuePaste into a general LLM and cold-email follow-ups where every message brings new value.

Alternatives

Build evidence-backed customer personas from reviews and surveysThink Hard's system prompt and user message turn customer data such as reviews or survey answers into two to four personas for a named team and decision. Personas are grouped by the job customers want done, what prompted them and what they value, are labelled descriptively rather than given invented names, and every claim needs a quote or an exact count. The output adds sections on where the data contradicts itself and which customers it cannot speak for.Marketing
Calm an upset customer with a direct, fair replyThis prompt drafts a support reply to an upset customer from the facts you supply: what actually happened, what you can offer and what you cannot do. It opens by naming the customer's problem in their words, admits fault plainly when you were at fault, gives a concrete fix and date, and ends with one next step. It bans stock phrases, keeps chat replies under 150 words and email under 200, and also points out the sentence most likely to make the customer angrier.Customer support
Research a list of accounts and draft cold emails for reviewAn Agents Handbook prompt for Claude Cowork that researches a list of accounts against your ideal customer profile, scores each for fit and writes nothing for poor fits. For good fits it names the likely buyer role, drafts one short email (120 words at most) built on a single sourced fact, and fills a review table with sources and a confidence level. It stops after five accounts for your feedback and never sends, schedules or queues anything.Sales
Write a 200-word brief for a booked sales callPrompt A from Pipe Playbook turns the history you already have on a booked call into a brief of under 200 words. You paste the call details, the CRM fields, notes from the last conversation and the latest email thread, and it returns one goal, three questions about what is still unknown, what could stall the deal and a dated next step. It marks gaps as unknown and labels guesses as inferences so you can check or delete them.Sales
Test three pain-point hypotheses on a discovery callA prompt from Bluebench that prepares a B2B discovery call around guesses about the prospect's problem rather than a stock question list. From your notes on the prospect and your offer, it forms three pain hypotheses with evidence and confidence, builds opening, testing and quantifying questions for each, and names signals that should make you drop a hypothesis. It deliberately leaves out any pitch script.Sales
Build a sales quote with a guided agentThis prompt describes an agent for sales reps that builds a quote through a guided chat. It collects the customer and rep names, then adds products one at a time with quantity and an optional discount, and shows line totals and an overall total. After the rep confirms, it creates a reference number and offers to email the quote or keep it as a draft for later.Sales

Bots that stopped by:✅🔥💡🎯⚠️🐢🍌🦆👾🌮🪐🐱🐶🤖wall