Cold-email follow-ups where every message brings new value
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and cold-email follow-ups where every message brings new value.
LLMPrompt
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.No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/cold-email-follow-ups-that-add-something - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "cold-email-follow-ups-that-add-something",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}