A Marketing Department of One
A property professional is their own marketing department. Listings to promote, posts across several channels, market updates. There is no team and no agency, only an hour on a Sunday evening.
The material that separates content people read from content nobody reads is the one thing no model has: what actually happened to that person this week. The closing that nearly fell through. The street where several houses sold in a fortnight. The question two different clients asked. It is in their head on Friday and gone by Tuesday.
From a Weekly Conversation to Finished Posts
The solution is built around a conversation, with scheduling as a small part of it.
- The appointment. The person picks one weekday and time, once, and the weekly session lands in their own calendar.
- The interview. An AI interviewer asks one question at a time and follows what the person says, the way a good journalist would. The call runs speech to speech. The person can speak, type or dictate, switch between them mid-conversation, hang up and pick it back up later the same week. The interviewer closes the conversation when the week is covered.
- The request. Generation starts when the person asks for it. They choose which channels the content is for.
- The posts. The platform writes one finished piece per channel, from what was actually said, applying that channel's rules while it writes. Each piece is written in the voice analyzed from the person's own answers, and each can be revised in its own conversation.
- The person. They edit, copy and post it themselves, and mark it as posted when they have.
Why Generic AI Writing Falls Flat
- A model with nothing new to say produces filler. Ask for a post about the local market and you get the same post every agent in that market can generate in the same minute. A weekly slot filled with filler is worse than an empty one.
- A tone preset is not a voice. A dropdown of friendly or professional is a sentence of catalog copy. A voice is how somebody actually writes: their register, how they open, the phrases they never use.
- Writing once and reformatting later fails every channel. Each channel has its own length, its own visible opening, its own hashtag habits and its own answer to whether a link is clickable. A piece reshaped afterwards fits none of them.
- Publishing with no review puts a reputation at risk. Here, what goes out carries a professional's name, in front of an audience they built.
Technology Stack
Writing and Testing Rules
The person's name goes on every post, so the person decides what is published.
- The interviewer leads the conversation. There is no question counter and no fixed script; the model follows the answers. Hard limits exist only to stop a call that never ends, and they are logged whenever they fire.
- Nothing is invented. The writing uses what the person said. A detail they held back in the interview is never added later by the writer.
- Presentation and identity stay separate. A style choice dresses a piece. It never replaces the analyzed voice of the person who is writing.
- Output is read by a person. Automated tests check the wiring. For the model's writing, a fixed, realistic dataset covering the full range of inputs is run against the real model, and a person reads the results one by one. Multi-turn conversations are held by hand, turn by turn.
What the Platform Is Set Up to Do
The figures here describe the platform as specified.
- One voice interview a week as the source of the week's content.
- Twenty publishing channels, each carrying the rules that bind it, applied while the piece is written.
- No post published without the person: the platform prepares the text, the person posts it.
- Generation from an interview only when the person asks for it.
- The interview is held in the language the person set, and follows them if they switch.
Who Else Has This Problem
Anyone whose own reputation is the brand, with nobody between them and their audience, is in the same spot:
- marketing is one more job for somebody who already has a full one;
- what makes their content worth reading is their own week, and it is never written down;
- the same message goes out on several channels, each with its own rules;
- their voice is the asset, and generic output damages it.
Mortgage and insurance advisers, recruiters, legal and accounting practices, clinics and coaches work under the same pressure. The interview can run on another schedule, and its output can feed other formats or a team's own publishing tools. The earlier AI content generation platform covered prompt recipes and brand voices for the same audience. Human-in-the-loop in our glossary explains why the person keeps the last step, and our generative AI development services page covers the build.
voice interview a week as the source of the content
publishing channels, each written to its own rules
ways to answer the interviewer: speak, type or dictate