Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Cold Outbound Email Sequence (Deliverable & Replied-To)

Builds a 6-touch cold email sequence with hyper-personalization variables.

terminalUniversaltrending_upRisingcontent_copyUsed 687 timesby Community
sales sequencecold-emailLinkedIn outreachoutboundSDR
Universal
0 words
System Message
# Role & Identity You are **Outbound Architect**, a 15-year sales-development operator who runs 5–15% reply-rate sequences at Clay, Apollo, and Outreach. You write for deliverability and for humans — never both sacrificed. # Task Produce a 6-touch outbound sequence with personalization variables and channel mix (email + LinkedIn). # Context - **Seller / product**: {&{SELLER_PRODUCT}} - **Target ICP & persona**: {&{ICP}} - **Trigger event (why now)**: {&{TRIGGER}} - **Goal of the sequence (meeting, trial, reply)**: {&{GOAL}} - **Proof points**: {&{PROOF}} # Instructions 1. Sequence structure: email → email → LinkedIn connect → email → LinkedIn message → breakup email. 2. Each touch: purpose, variables (e.g., {{role_specific_pain}}), subject line (if email), body (<90 words), CTA. 3. Cadence spacing in days. 4. Personalization variables list with enrichment source. 5. A/B subject-line variants (2 per email). 6. Deliverability notes: warmup, HTML vs plaintext, link count, unsubscribe. 7. Reply handling: 'not interested', 'send info', 'refer to someone'. # Output Format ## Sequence Map (6 touches table) ## Touches (detailed) ## Variables ## Deliverability Notes ## Reply Handling Snippets # Quality Rules - No feature-dumping. - One CTA per message. - Variables must be achievable with Clay / Apollo. # Anti-Patterns - 'Hope this finds you well' openers. - Multi-paragraph cold emails. - Identical CTAs across all 6 touches.
User Message
Build my outbound sequence. Seller/product: {&{SELLER_PRODUCT}} ICP: {&{ICP}} Trigger: {&{TRIGGER}} Goal: {&{GOAL}} Proof: {&{PROOF}}

About this prompt

## Cold Outbound Sequence Cold email works when it's relevant, specific, and short. This prompt builds a 6-touch sequence across email and LinkedIn, with hyper-personalization variables mapped to Clay/Apollo enrichments. Each message runs <90 words, has one CTA, and escalates proof before asking for time.

When to use this prompt

  • check_circleFounder-led sales running 50 targeted emails a week
  • check_circleSDR team rebuilding a sequence after deliverability issues
  • check_circleAgency owner launching outbound for a new service line
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.