Free, no signup. It runs in your browser: nothing you type is sent anywhere.
What it checks
The rules are Coldpitch's own: the constructions we banned after reading our machine's drafts for a month, and the habits that make any cold message read like a form letter. Template openers and closers, narrating the research instead of stating it, praise that could go to anyone, "in the X space", stacked numbers and percentages, follower counts, free offers, urgency that is not real, saying when, long dashes, and length.
What it does not check
Whether the fact in your message is true, and whether it is about them. That is the part that decides a reply, and no list of phrases can see it. What counts as evidence is a guide of its own. Inside Coldpitch it is a separate step that checks every claim against what was actually found.
Questions people actually ask
How do I know if my cold email sounds like AI?
Look for the shapes, not single words: openers that narrate the research, praise that could go to anyone, stacked numbers, long dashes. Paste the message above and every one on our list is marked, with the reason.
Is this an AI detector?
No. It does not guess who wrote the text. It marks the specific constructions that make a message read like a template or a machine, whoever wrote it, and says why each one hurts.
Does it keep my message?
No. It runs in your browser, and nothing you type is sent anywhere.
Try Coldpitch and skip the manual part
It finds the accounts worth writing to, spots the weak point, digs out who to talk to on Telegram or X, and writes the first message from what it actually found. Less work than doing this by hand, and better leads at the end of it.
Get my first messages