AI Property Consultant · Personal build, in daily use · Gold Coast, AU
My rentals. My own system.
Before I sell a workflow to a property agency, it has to survive my own rentals first. This system drafts real Marketplace replies in my voice, tracks rent and inspections, and uses human approval in the demonstrated enquiry flow.
- Best for
- Property managers and agencies answering the same enquiries every day.
- Problem
- Every listing draws the same “is this still available?” trickle, answered by hand.
- Changed
- Replies drafted in my voice within moments — I approve before anything sends; rent, bills, and inspections tracked.
No tech knowledge needed · 15 minutes · you keep the map either way.
What was I actually solving?
Every listing draws the same trickle of “is this still available?” messages, most of them asking what the ad already says. Answering by hand, or leaving people on read until I got to my phone, was quietly losing me tenants — so I built the fix for my own rentals first, and only offered agencies what had already survived my own doors.
The proof
One enquiry, start to sent.
Reconstructed from a real Facebook Marketplace thread, anonymised. The message that came in, the reply my system wrote in my voice, and the tap that let it send.
The system held that draft and asked me: approve, edit, or skip. Nothing reached the tenant until I tapped approve. That gate is part of the demonstrated enquiry flow.
Verbatim transcript of the clip
Hey guys, just wanted to show you a quick example of one of the workflows I used and built myself to make my property managing a lot more easier, and it wouldn’t take so much time out of my day. So here is a common issue I’ve been facing, which is so many people just keep asking if it’s available and whatnot. Well, the information is already on the post and you don’t really want to keep spending your time out of your day to tell them, “oh yeah, it’s available,” just for them to ghost you or ask more questions. So here is the system that I’ve built. So as you can see, it’s asking me approval before sending the response, and I worked on the iteration on improving the response. So as you can see, the message is improving.
Public-cut note: the video ends at the approval gate and excludes the original discussion of private example conversations. Any customer deployment must exclude unnecessary personal details and agree the permitted sources, access, retention, and approval rules before use.
What does it do, day to day?
- Tracks rent and bills as they fall due, so nothing slips past its date
- Plans inspections and flags lease renewals, checked against the market
- Drafts replies to rental enquiries in my own voice — I approve, then it sends
- Helps list a property: drafts the ad copy and the replies, never posts on its own
- Uses approved example messages as drafting context, without retraining the base model
Everything it writes is a draft until I approve it.
The outcome
What changed once it was running?
The trickle of enquiries stopped being an interruption. A message lands, a reply is drafted in my voice within moments, and all that’s left for me is a glance and a tap — or an edit if I want one. The rent, the bills, the inspections and renewals are tracked as they come due instead of living in my head and a spreadsheet. I still make every real decision; I’ve just stopped doing the typing and the remembering. It’s the same shift I sell to agencies — except here I’m the one who felt it first.
| Before / After | Before | After |
|---|---|---|
| Enquiry replies | Typed by hand, whenever I next picked up my phone | Drafted the moment a message lands; I approve and it sends |
| The reply’s voice | Only sounded like me if I wrote it myself | Uses approved examples as context and aims to match my voice |
| Rent, bills, inspections | Tracked in my head and a spreadsheet | Tracked as they fall due, surfaced before they slip |
| Who decides | Me, doing all of it | Me approving — the system does the legwork |
What happens before anything sends?
It cannot move money and never touches trust accounting. Every reply, post and update is a draft first, and a person approves anything that matters.
- Human approval points
- Sensitive actions wait for a person to sign off before anything sends or triggers.
- Escalation rules
- When something falls outside the rules, the system hands it to a person instead of guessing.
- Logs and visibility
- In-scope actions are recorded where connected tools expose the required events.
The questions I actually get asked.
- Is this used by a real agency, or just your own rentals?
- Right now, my own. This internal build informs the property workflow approach I offer to agencies. Any agency version would be scoped separately around that team’s software, permissions, and approval rules.
- Does it touch trust accounting or move any money?
- No. It has no access to move money and nothing to do with trust accounting. It drafts replies, tracks dates, and organises information; a person approves anything that matters.
- Who approves what the AI writes?
- On my own portfolio, me. For an agency build, the written scope identifies the property manager or principal who approves sensitive and first-time actions.
- Does it ever send a message on its own?
- By default, the demonstrated flow waits for approval. After review, I can explicitly enable a specific low-risk reply inside written rules; those sends and approval decisions remain visible in the workflow record.
Proven on my own doors, before it is offered to anyone else.
Bring me the messages, the chasing and the reporting your team keeps working around. I will map it and tell you what should be automated first.
No tech knowledge needed · 15 minutes · you keep the map either way.