Five sentences, line by line.
Five sentences carry four things: who is writing, for whom, why this person now, and how to say no. A stranger can judge it at a glance.
- From
- Dylan, AI agent for Harrow Line
- To
- Maya, VP Operations, Nordfeld Logistics
- Subject
- fuel across your ohio sites
Hi Maya, I'm Dylan, an AI agent working with Harrow Line. I'm writing because Nordfeld just opened a second warehouse in Ohio, and a new site usually means new fuel cards. Harrow Line puts every vehicle on one card with its own spend limit. Would a 20-minute review of your fuel spend be useful? If not, reply "no" and I won't write again.
Dylan, AI agent for Harrow Line
63 words · lowercase subject · says he is an AI agent in the first line
- From
- The From line reads "Dylan, AI agent for" the client's name.
- Subject
- Lowercase, the way a person types it.
- Who is writing, and for whom
The disclosure costs nine words, and it sits in the first line, not in small print under the signature.
- Why this person, now
Pretending to be human does nothing for relevance; a specific reason to write does.
- What the company sells
In one line, as your brief puts it.
- One small ask
What the prospect gets comes from your meeting definition. A concrete offer gives the reader a reason to say yes.
- How to say no
Any reply stops every further scheduled email to that person, by rule, before any AI sees it.
The companies and the person are invented.
Short, plain, and in the first person.
Dylan's voice is plain, confident and specific: short sentences, American spelling, no hype. Dylan is he, and he writes in the first person.
Dylan says he is an AI, first.
In the first sentence of every first email, on the page and in replies. Never a fake name, never a fake person.
Hi Maya, I'm Dylan, an AI agent working with Harrow Line.
Hi Maya, Sam here from the team. Quick question about your fleet.
Subject lines are lowercase.
The way a person types them. No fake "Re:" pretending to continue a conversation.
fuel across your ohio sites
Quick Question About Your Fleet!!
Times read like a calendar.
24-hour times, the day and the date, the zone wherever a meeting is booked.
Booked: Thursday, Oct 22, 10:30 Eastern.
Next Thursday at 10.30am-ish?
What is missing matters too: no "just following up on my last note" when there was no last note.
His mailboxes. Your approval.
From his own domains
Dylan writes as an AI agent working for you, from his own warmed domains and mailboxes, with a separate slice for each client. Your domain never sends a cold email.
You approve the first emails
You approve the plan and the first emails of every new angle. Each angle is a new promise in your name: a new claim, a new reason, a new tone. You see every promise once before it is repeated at scale.
Routine replies he answers. The rest come to you.
He answers routine replies himself, such as scheduling or questions your brief answers, and hands you anything about pricing, legal or complaints.
When someone replies, every further scheduled email to that person stops the moment the reply is read, by rule, before any AI sees it. Only then does Dylan read it.
Got an email from Dylan?
Then an AI agent wrote to you on behalf of the company named in the email, and you can end it in one step. Reply "stop" to any of his emails and he stops.
If you would rather no client of his ever writes to you, leave your address on our site. Your request is recorded at once and can take up to 2 business days to reach every campaign.
See the first email he would send for you.
Tell Dylan your website and who you want to meet. Your plan shows the first email he would send, and nothing is sent without your approval.
Already know your definition? Send the full brief