You get:
- low open rates (subject line problem)
- low reply rates (value or CTA problem)
- low meeting rates (offer or qualification problem)
- no diagnosis — just guessing
- same mistakes repeated across campaigns
But performance analysis is not guesswork.
It is systematic diagnosis.
- Low opens: subject line, sender name, timing
- Low replies: hook, value proposition, personalization
- Low meetings: offer, CTA, qualification
- High unsubscribes: frequency, relevance
Without diagnosis, you fix the wrong thing.
This framework forces AI to diagnose cold email problems.
Assume the role of a cold email analyst who diagnoses performance issues. Your task is to analyze cold email performance and recommend fixes. Generate: 1. OPEN RATE DIAGNOSIS - Current open rate - Benchmark (good: 40-60%) - Likely causes (subject line, sender name, timing) - Specific fixes 2. REPLY RATE DIAGNOSIS - Current reply rate - Benchmark (good: 5-15%) - Likely causes (hook, value prop, personalization) - Specific fixes 3. MEETING RATE DIAGNOSIS - Current meeting rate (from replies) - Benchmark (good: 20-30% of replies) - Likely causes (offer, CTA, qualification) - Specific fixes 4. DELIVERABILITY DIAGNOSIS - Spam score potential - Likely issues (spam words, attachments, links) - Specific fixes 5. OVERALL RECOMMENDATIONS - Top 3 things to fix first - A/B test suggestions INPUTS: Email Campaign Data: - Open rate: [INSERT %] - Reply rate: [INSERT %] - Meeting rate (from replies): [INSERT %] - Unsubscribe rate: [INSERT %] - Sample size (emails sent): [INSERT NUMBER] Email Content (paste or describe): [PASTE OR DESCRIBE] Target Audience: [INSERT] Sender Name/Email: [INSERT] RULES: - Open rate below 40% = subject line or sender problem - Reply rate below 5% = hook or value problem - Meeting rate below 20% = offer or CTA problem - Benchmark against industry averages - Fix one problem at a time (A/B test) - Track metrics before and after changes
- Open rate below 40%: test subject lines and sender name.
- Reply rate below 5%: test hook and value proposition.
- Meeting rate below 20%: test offer and CTA.
- Fix one problem at a time (A/B test).
- Track metrics before and after changes.
Email Campaign Data:
– Open rate: 22%
– Reply rate: 1.5%
– Meeting rate: 10% (of replies)
– Unsubscribe rate: 0.5%
– Sample size: 1,000 emails sent
Email Content: Standard value-first email about CRM automation for VPs of Sales
Target Audience: VPs of Sales at B2B SaaS companies
Sender Name/Email: “Alex from CRMPro” / alex@crmpro.com
This framework improves outcomes by forcing:
- open rate diagnosis (subject line, sender)
- reply rate diagnosis (hook, value)
- meeting rate diagnosis (offer, CTA)
- deliverability diagnosis (spam)
- prioritized recommendations (focus)
Great cold email performance doesn’t come from guessing — it comes from diagnosing and fixing.
Build Better AI Systems
Subscribe for advanced prompt engineering, AI sales tools, cold email frameworks, and practical strategies for sales professionals and founders.