---
name: 3-step-ai-generated-cold-email-sequence
description: >-
  A three-email cold sequence for one persona, short and direct, built from your account research to start real conversations. Adapted from Christian Krause.
  Task type: Create. Built for Sales.
  Use when the request sounds like "3-Step Cold Email Sequence".
  Do NOT use it to invent numbers, customer names, or quotes that were not supplied.
license: MIT
metadata:
  author: The Revenue AI Report
  suite: Account Research and Targeting
  version: "1.0"
  source: https://www.therevenueaireport.com/prompts/3-step-ai-generated-cold-email-sequence
---

# 3-Step Cold Email Sequence

A three-email cold sequence for one persona, short and direct, built from your account research to start real conversations. Adapted from Christian Krause.

One job only: a three-email cold sequence for one persona, short and direct, built from your account research to start real conversations. Anything outside that job belongs in another file in the Account Research and Targeting suite.

## When to use this skill

- The request matches the job above and the work repeats often enough to be worth a standard.
- You have, or can ask for, the inputs listed below.
- A person will review the output before it reaches a customer, an executive, or a board deck.

## When not to use it

- The answer needs a number, a benchmark, or a quote nobody supplied. Ask for it instead of producing one.
- The task is a different job in the same suite. Open that file rather than stretching this one.
- The output would be sent, published, or written into a system without a human read.

## Inputs to collect first

- persona
- company research
- email1
- email2
- email3

Ask for anything missing before running. Do not fill a gap with a plausible guess.

## Process

1. Confirm the job, the audience, and the decision the output feeds.
2. Collect the inputs above. Name anything still missing out loud.
3. Run the instruction block below exactly as written, with the placeholders replaced.
4. Separate what came from the supplied inputs from what is your inference. Label the inference.
5. Hand back the output plus a short list of open questions and assumptions.

## Instruction block

Run this text with the placeholders filled in.

```text
Your task is to write a sequence of 3 cold emails to the persona of a company, following specific rules and a given structure.

The rules for writing the cold emails are:
- Subject line should be 2-3 words, in small caps, looking like an internal email
- Email should be no longer than 100 words 
- Email should be written in simple language, grade 6 reading level or below
- Email should include zero formality, fluff or filler words
- Email should include only 1 question at the end

The structure for the 3 emails is:
- Email 1 highlights a research observation and builds a link to a hypothesis about a business challenge relevant to the persona. It asks for validation of the hypothesis.
- Email 2 highlights the business impact of this problem from the point of view of the persona. It asks for interest to engage in a conversation.
- Email 3 delivers a high level value proposition of your solution and clearly links it to the stated problem. It asks for interest to learn more.

First, read the provided information about the persona and company research:

<persona>
{$PERSONA}
</persona>

<company_research>
{$COMPANY_RESEARCH}
</company_research>

Using the persona details and company research, write the 3 cold emails following the given rules and structure. Try to include rich research insights and persona-specific language within the constraints.

Write email 1 inside <email1></email1> tags, email 2 inside <email2></email2> tags, and email 3 inside <email3></email3> tags.
```

## Decision rules

- Supplied evidence beats inference. If the two disagree, say so and keep the evidence.
- Unknown is a valid answer. Write "unknown" rather than estimating.
- Keep one recommendation per output. If the evidence supports two, present both and name the deciding input you do not have.
- Match the reading level of a working operator. Short sentences. Explain any term the reader may not use daily.

## Quality checks

- Every number, name, date, and quote traces to an input the user supplied.
- No vendor claim is repeated as fact without naming the source.
- Assumptions are listed separately from findings.
- The output answers the original request and nothing else.
- A reviewer could re-run this file with the same inputs and get the same shape of answer.

## Guardrails

- Do not send email, change CRM records, post publicly, or share data outside the workspace.
- Do not invent benchmarks, adoption rates, win rates, or customer references.
- Flag anything that needs a human decision instead of deciding it.

## Source

- Prompt page: https://www.therevenueaireport.com/prompts/3-step-ai-generated-cold-email-sequence
- Suite: https://www.therevenueaireport.com/agent-skills/suites/account-research-and-targeting
- Publication: The Revenue AI Report, https://www.therevenueaireport.com