Outreach Without Spam: score first, research the pitch, draft in small batches, a person sends
by PaperChaseWebb
A prompt pack and method for founders, consultants and small agencies. A scoring rubric you write, a pursue or pass threshold, research cards from the prospect's own public record, a four-part pitch, a sales brain file, enrichment with evidence labels, a compliance and deliverability floor, reply triage, a Grok Bot outreach desk persona, written refusals, a defensive check for manufactured intros, a failure table, a worked example, a rules block and 14 prompts.
- Price
- $29
- Difficulty
- Beginner
- Setup
- 1 hr
- Format
- .md file
outreach-without-spam-ai-prospecting-with-a-human-send.md · 18 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
Agents score, research and draft your outreach in small batches built on real details, and you read and send every message yourself.
What you get
- 16 sections in one .md file
- A rubric template and a pursue or pass threshold
- Research cards with evidence labels
- The four-part pitch
- A sales brain file outline
- A compliance and deliverability floor
- A reply triage table
- A Grok Bot outreach desk persona (also for Claude, Codex or Hermes)
- Refusals written in advance
- A defensive check for manufactured intros
- A failure table and a worked example
- A rules block and 14 prompts
Who it is for
People who want AI doing the prospecting and drafting work without it ever sending a message in their name.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: The pack is the only purchase. Uses the assistant and mailbox you already have.
Time to result: First scored list and batch of drafts the same day
How it works
Write the brief and rubric
Prompts 1 and 2. Who it is for, who it is not for, and how a prospect earns a score.
Expected: A rubric you could defend line by line.
Set the line and score
Prompts 3 and 4. Write the threshold before the first score.
Expected: A sorted list where everything under the line is a pass.
Research and draft
Prompts 5 to 8. No real detail, no draft.
Expected: Short drafts built on Seen facts only.
Check and send
Prompts 9 and 10, then you send from your own mailbox.
Expected: A small batch you read in full.
Review
Prompt 14 suggests one rubric change from the log.
Expected: A better rubric, changed on purpose.
Sample prompts, free to use
Score every row in this list against my rubric [paste]. One sentence per criterion. Sort by total. Mark everything under [threshold] as pass. Do not research or draft anything yet.
Drafting only happens above the line.
Check this draft against its research card and my brain file. List any fact not on the card, any banned phrase, missing compliance lines, anything personal and anything that sounds like a template. Do not rewrite it.
The agent lists; you decide and you send.
Free preview of the file
# Outreach Without Spam: score first, research the pitch, draft in small batches, a person sends A prompt pack and working method by PaperChaseWebb for founders, consultants and small agencies who want AI agents doing the research and drafting on outreach without letting them near the send button. A one-page system, a scoring rubric you write yourself, a pursue or pass threshold, a research step that quotes the prospect's own public record, a four-part pitch, a sales brain file loaded once, enrichment with evidence labels, a compliance and deliverability floor, a reply triage desk, a Grok Bot outreach desk persona, refusals written down in advance, a defensive check for manufactured intros, a failure table, a worked example, a rules block and 14 prompts. Plain .md. Works in Grok Bot, Claude, ChatGPT, Claude Code or Codex. Most AI outreach systems are sold on volume: thousands of "hyper-personalized" emails a day, on autopilot, while you sleep. That is how sending domains get burned, how a wrong "fact" about a stranger ends up in their inbox under your name, and how a brand that took years to build gets spent in a week. What works is the opposite shape: fewer people, chosen against a rubric, pitched about something they have said they care about, in small batches, with a person reading and sending every message. This is a working method, not legal advice. Email and messaging law differs by country and changes. In the US, commercial email falls under CAN-SPAM; many other pla
Worth knowing
- Not legal advice. Email and messaging law differs by country and changes. Check the current rules and ask counsel before any volume.
- No method guarantees replies or revenue.
- Results and tools quoted from other creators are their claims and were not verified.
Questions
Does this send emails for me?
No. Agents score, research and draft. You read and send every message from your own mailbox.
Can I use it with Clay or a sending tool?
Yes for research and drafts. Keep any autopilot or auto-follow-up setting off, and use a separate, authenticated, warmed sending domain.
Do I need Claude Code or Codex?
No. Every prompt works in a chat assistant. The outreach desk persona is ready to paste into a Grok Bot, a Claude project, a Codex agent or Hermes.
Details
Version 1.0 · Updated Oct 27, 2026 · Markdown version of this page
License: Personal and commercial use for your own business and your clients' outreach. Do not resell or republish this pack. Download terms
Related
The outreach rubric and the four-part pitch (free sample)
The one rule for outreach agents, a five-criterion starter rubric with a pass line, the four-part pitch and a check prompt.
Workflow, Not Wrapper: test an AI product idea, shape the offer and set the price
A prompt pack and method for anyone building or selling on top of a model. A seven-score absorption test, a one-page workflow product spec, a problem mining loop, a channel translation table, a model column check, an offer ladder with pricing rules, a check for copied success stories, a fidelity gate for generated output, a failure table, a worked example, a rules block and 14 prompts.
AI Receptionist and Booking Agent Template: script, capture, escalation and test calls
A bot template for a phone receptionist that answers missed calls for a local service business, says up front it is an AI assistant, books from a fixed service list into the real calendar, texts a confirmation and hands everything else to a person. Includes a call map, persona and script, ids-only booking checks, an escalation table, a disclosure and never-commit sheet, 12 test calls, an owner run sheet and 14 prompts.
Check the Claim (expanded edition): a method, prompts and a skill for checking AI claims
A Markdown pack that makes your agent check income, tool, popularity, quote and funding claims before they reach a brief, a purchase or a post: arithmetic first, primary sources second, one honest verdict per claim.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.