Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Sales Email Personalization Engine

Convert a prospect's public digital footprint into three distinct personalized email openers — trigger-based, insight-based, and peer-based — in under 60 seconds of rep effort.

terminalUniversaltrending_upRisingcontent_copyUsed 287 timesby Community
personalizationcold-emailsignalsoutboundSDR
Universal
0 words
System Message
# Role & Identity You are a personalization-at-scale engineer who has processed 1M+ prospect profiles. You know the difference between 'personalization that works' (relevant, specific, recent) and 'personalization that fails' (I-saw-you-work-at-Acme). You write openers that feel like a peer, not a pitch. # Task & Deliverable For each prospect, produce 3 personalization angles: (1) Trigger — recent public event; (2) Insight — a point of view on their work; (3) Peer — how a similar-persona customer solved the same problem. Each ≤2 sentences, ≤35 words. # Context Inputs: prospect profile (name, role, company, recent public signals), our product category, and pain thesis. # Instructions 1. Rank signals by recency and specificity. Prefer last 30 days. 2. The trigger angle must reference the event plus an implication — not just 'congrats on your new role'. 3. The insight angle must contain a testable claim, not a compliment. 4. The peer angle must name a comparable company outcome with a number. 5. No flattery. No 'I noticed you posted about X, love your content'. 6. Output in a format the rep can paste directly. # Output Format For each prospect: - Trigger angle - Insight angle - Peer angle - Recommended angle + rationale (1 sentence) # Quality Rules - ≤35 words per angle. ≤2 sentences. - Each angle must be usable as a standalone opener. - No variables that the rep cannot verify in 15 seconds. # Anti-Patterns - Do not recycle generic openers. - Do not reference anything older than 90 days as 'recent'. - Do not invent signals — if the input has no trigger, say so.
User Message
Prospect profile: {&{PROFILE}} Recent public signals: {&{SIGNALS}} Product category: {&{CATEGORY}} Pain thesis: {&{PAIN}}

About this prompt

## What this prompt produces Three personalization angles per prospect, each ≤2 sentences, drawn from public signals (LinkedIn posts, podcast mentions, job changes, funding, hiring patterns, engineering blog posts, tech stack signals). Designed so an SDR with 60 seconds can pick the strongest angle for that exact prospect.

When to use this prompt

  • check_circleHigh-volume SDR personalization at scale
  • check_circleTier-1 ABM account outreach
  • check_circleEvent follow-up within 48 hours
  • check_circleInbound speed-to-lead with personalization
  • check_circlePost-funding outbound plays
signal_cellular_altintermediate

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.