If you could pick one place in your business to start, pick your email. Not because it's the most exciting place — it isn't — but because it's the place where you'll know within two weeks whether this works.

That's a bigger advantage than it sounds. Most AI projects don't fail on technology but on the lack of a yardstick. With email you have one right away: you see per draft whether it's right, and you know exactly what you would have written yourself.

01 / the definitionCan AI write my business emails?

Yes, as a draft. The system reads the incoming email, extracts the question, and writes a reply based on how you answered similar messages before. That draft sits ready in your own mail program. You review, adjust and send. The final word stays yours.

What it doesn't do is reply on its own. A reply to a customer is a statement with your name under it, and that belongs in front of your eyes. Why that boundary isn't an option but a build decision is explained in why we never publish automatically.

02 / the choiceWhy start with email and not with content or sales?

Because the inbox combines three traits that don't come together anywhere else. Volume is high: email arrives every day, unasked, whether you feel like it or not. Patterns are strong: most of your replies resemble earlier replies. And the yardstick is sharp: you see per draft within ten seconds whether it lands.

Content and sales don't have those three. One blog post per week gives a system little practice material and gives you few reference points — you only know in a quarter whether it did anything. Fifteen emails a day give you both, immediately.

The inbox isn't the most impressive place to start. It's the most instructive.

There's another reason, and it's less cheerful. Email is usually the work that happens in the evening. Not because it's important, but because it's what's left over. That's exactly the kind of work a system should handle: high in volume, low in judgment, and it eats the attention you wanted to save for something else.

03 / the sourceWhere does such a system get your tone from?

From two sources that complement each other. The first is your sent folder: that shows how you actually write, not how you think you write. The second is a conversation in which you explain what you do and why — that delivers the reasoning that in your emails is only visible as an outcome.

That second step is often skipped, and that's the weak spot of "read my last two hundred emails". Sent mail gives you tone. It doesn't give you judgment. Your archive shows that you gave that one customer a discount, not why you did that back then and why you wouldn't do it for the next one. A system that only knows your archive copies your style and guesses your reasoning.

That's why we record it the other way around. Not with a questionnaire but with a recording:

What you end up with isn't a folder of files but a knowledge layer: the place every draft is written from afterward. Your sent mail determines how it sounds, the conversation determines what's in it.

04 / the wordWhy don't we call this "self-learning"?

Because it doesn't learn by itself. In this category "self-learning" has become a common word and it's accurate in almost no case. What happens is that the system improves from your corrections. Without corrections, nothing happens. "Self-learning" suggests it happens automatically, and that's exactly the expectation people drop off on.

The honest word is correctable. If you adjust the same wording three times, that adjustment should become the default. That's not magic and it's not a model's mistake either — it's how your judgment enters the system. The correction loop is the learning mechanism, and you are its engine.

That difference matters when you're choosing. A system that learns by itself doesn't need maintaining. A system that's correctable asks you for a fixed moment each week where you talk or type into it what's changed about your offer, your target group or your way of working. Without that moment the knowledge layer quietly ages, and you only notice once the drafts start feeling off.

05 / the catchWhat goes wrong in the first weeks?

You correct a lot. Drafts are then too formal or too loose, they miss context only you have, or they neatly answer the wrong question. Expect a few weeks where reviewing sometimes takes as long as writing it yourself. That's not a malfunction, that's the period where the system is getting to know you.

This is the caveat missing from most sales pitches, and it's the reason people drop off in week two. Whoever knows the dip in advance can get through it. Whoever buys a system that's supposed to be perfect from day one buys a disappointment with an invoice attached.

Then it turns. The drafts get sharper, your role shrinks to reading, changing a sentence here and there, sending. When that turning point comes depends on how much email you have and how consistently you correct — we won't put a number of weeks on that, because anyone who does can't actually know it.

06 / honestWhat shouldn't be part of the promise here?

A few things, and we'd rather name them ourselves. This is exactly the point where a blog post can easily promise more than a vendor delivers.

• No hours-saved promise. "Save eight hours a week" is the promise framework of nearly every vendor in this market, and nobody can know it in advance. It depends on your email volume and on how much of your replies actually resemble each other.
• No replacement of your judgment. The system suggests what you'd probably answer. Whether you give that discount, take that assignment or have that conversation stays your work.
• No fix for an unclear offer. If you're not yourself sure what you sell to whom, a system only speeds up that confusion. That's not a reason to wait, but it is a reason to look at that first.
• No guarantee every message is suitable. Email with a lot of context that only exists in your head, or a sensitive matter where tone is everything, stays manual work. The system is good at the pattern, not the exception — and it should show you which of the two it thinks it's dealing with.

With us, the mailbox falls under the Back Office: one of the fixed roles in the system, not a separate project bolted on. What you get isn't an email assistant then but one crew member set up on your knowledge layer, alongside the roles carrying your content, your meeting notes and your lead follow-up.

The mailbox stays yours in this. The system works in your account, not in an environment of ours that you get a login for. If you cancel, you keep your mail, your archive and everything that happened in it.

This text was created with AI assistance and reviewed and approved by a human before publication.