Cold-email slop is fake personalisation. The phrases below exist to imply the sender looked you up, while saying nothing that proves it. Recipients learned this pattern faster than any other, because they get it twenty times a week.
The phrases, and what to write instead
| Avoid | Write instead |
|---|---|
| I hope this email finds you well | Delete. Start with why you are writing. |
| I hope you're doing well! | Delete. |
| I came across your impressive work | Name the exact thing, and what you thought about it. |
| I saw your profile on LinkedIn and was impressed | Cite one specific fact. Otherwise leave it out. |
| I wanted to reach out | You are reaching out. Say the thing. |
| Quick question | Ask the question. Put it in the subject line. |
| Just circling back | "Following up on the 3rd — did that reach you?" |
| Just bumping this to the top of your inbox | Say what changed since last time, or do not send it. |
| Dear Sir or Madam | Use their name. If you do not have it, you are not ready to send. |
| leverage synergies | Say what you would actually do together. |
| optimize outcomes | Name the number you think you can move. |
| a robust, seamless solution | Name the capability and the setup time. |
| Here's the truth: | Cut. Then say the thing. |
| I'd love to pick your brain | Ask one specific question you cannot answer yourself. |
| Let me know if this resonates | "Worth 15 minutes on Thursday?" |
Score this draft before you send it
Paste your text into Slop Score. It checks every rule on this page plus the full 200+ list, marks each hit in place, and cleans the mechanical ones. Runs in your browser; nothing is uploaded.
Check my draft →The rule underneath all of them
Every replacement above does the same thing: it swaps a claim for evidence. That is the whole method, and it is why no tool can finish the job for you. A model can delete results-driven. Only you know the number that belongs there.
Density is what readers notice, not any single word. One phrase from this table is a coincidence. Four in a short piece is a pattern, and people now recognise the pattern quickly. The full 200+ tell list covers the vocabulary, sentence patterns and machine artifacts that apply everywhere, whatever you are writing.
Questions
Why do AI-written cold emails get ignored?
Because they follow a shape the recipient has seen hundreds of times: warm opener, vague compliment, unearned ask. The words are polite and the structure is transparent. An email that opens with a specific fact about the recipient's situation gets read even when it is blunt.
What makes a cold email subject line sound automated?
Fake urgency ("Quick question", "Following up"), and anything that could be sent to any recipient. A subject naming the recipient's actual situation reads as human because a bulk sender could not have written it.
Can I use ChatGPT for cold email without it sounding automated?
Use it for the structure, not the specifics. Every sentence that mentions the recipient has to come from you, because that is the only part the model cannot know. If you let it write the personalised line, it will produce a compliment that fits anyone.