Send 500 AI-written cold emails and iterate the prompt with 40-prospect tests, for sponsorship sales
A paid newsletter post says a prompt reverse-engineered from replied-to emails produced 167 replies and 43 meetings from 500 sponsorship cold emails, with each prompt version tested on 40 prospects.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
Selling sponsorships by cold email gets very low replies when the emails read as templated or AI-written.
What was tried
The author studied seven cold emails they had replied to out of about 1,000 received, and built a prompt with six structural blocks (pattern interrupt, earned insight, relevance bridge, an offer with little cost to the recipient, a low-stakes ask and a signature without sales language). The prompt rejects output that lacks a specific non-public observation about the prospect and removes common AI tells. Eleven versions were tested on batches of 40 prospects and versions that did not raise reply rate were rolled back, and follow-ups were sent.
What was reported (positive)
The author reports 167 replies, 43 meetings, 11 closed at an average of $8,500 and $94,000 in sponsorship pipeline from 500 emails over 17 days, for about $11 in API tokens and four hours of work. They say the first follow-up produced 21% of replies and later follow-ups produced none plus spam reports.
Limitations
This is a single-sender, self-reported story in a paid post that sells the prompt, with no independent verification. The numbers have inconsistencies (such as the baseline reply rate) and 'pipeline' and 'closed' revenue are mixed. List sourcing, the model, sending setup and most sample sizes are not given, results may not carry over from sponsorship sales to other industries, and the author admits about 8% of generations are still wrong.
What you need
A language model account, a prospect list and a sending setup with warmed domains (covered in the paid section). Setup is described as about 90 minutes.
Sources
- Future Insider (Substack) ↗ Firsthand write-up, published May 25, 2026
Source published: May 25, 2026. Last reviewed here: October 11, 2026. Spot a mistake? Tell us.
Related workflows
Research sponsors, build a sponsorship CRM and schedule checks with the Manus agent
A content creator used Manus to find companies advertising in AI newsletters, build a web-app CRM for YouTube sponsorships, and schedule recurring lead and trend checks.
Cut long podcasts into vertical clips with Whisper, Claude scoring, YOLO reframing and n8n
An architecture write-up of an in-house media tool that transcribes podcasts with Whisper, has Claude score the best moments for each brand's audience, reframes video to vertical, and keeps humans in the loop.
Run a scheduled n8n workflow that scrapes leads, checks their GitHub bio and sends GPT-4o-mini cold emails
A builder documents a 21-node n8n workflow that scrapes freelance developer leads, validates emails, looks up a GitHub bio, writes a personalised email with GPT-4o-mini and sends it with pauses between messages.
Personalise cold emails with a single LLM call on a scraped page, and use a soft 'reply YES' ask
A custom-agent studio explains why one LLM call with the full scraped website beat a multi-step chain for cold email personalisation, and why changing the call to action mattered more than the personalisation.