Repair reporting for landlords who can't be on the phone all night

Most problems with repairs start before anyone picks up a tool.

• Details go missing. Which property, which room, since when, getting worse or not. Without them, the first visit is a fact-finding trip.
• Urgency is guessed. A tired person at 10pm has to decide whether "there's a funny smell near the boiler" is a Monday job. That decision shouldn't rest on how the call happened to go.
• Promises get made that nobody can keep. "Someone will be round first thing" calms a tenant down for an hour and causes a complaint the next day.
• There's no record. When a tenant says they reported it three weeks ago, you need more than your memory and a message thread.

None of these needs a bigger team. They need the same questions asked every time, clear rules for what's urgent, and a written record.

It takes the details properly. The assistant collects the caller's details and turns what they say into a structured repair request, rather than a loose message you have to decode later.

Rules, not the AI, decide what happens next. Safety, the progress of the job and approvals are decided by fixed rules on our server. The AI can't override them, however the conversation goes.

Dangerous reports are held for a person. Reports our rules flag as safety-critical can enter escalation and human review instead of the routine queue. They're latched, and only an authorised person can clear them. Our safety rules page explains how this works, and why the list of report types isn't published yet.

Emergency guidance is UK guidance. Where there's an immediate danger to life, the assistant's guidance is 999, never 911.

Everything leaves a trail. Consequential actions leave audit evidence alongside the job, and the system only reports something as done when there's evidence it succeeded.

This is the part tenants notice. The assistant must not invent:

• a booking or appointment time
• that a contractor has been sent
• a refund, compensation or a waived fee
• account information
• a safety reassurance such as "it'll be fine till Monday"

If nothing has been arranged, it won't say it has. MaintenanceOS also has no authority to move money. Quotes and invoices go through checks, but there's no payment, refund or compensation in the system at all. (No client-money execution authority.)

If a tenant asks for a person, they can ask to be transferred (live transfer handling is still under testing). If something goes wrong technically, the system is built to fail safe rather than quietly pass the call somewhere unplanned. Not a live always-on phone.

The basics matter more, not less. A larger landlord usually has a repairs desk. A smaller one has a mobile phone and a day job. Your legal duties as a landlord are the same either way, and they stay with you whatever tools you use. What a tool can do is make sure reports are captured the same way every time, dangerous ones are put in front of you or the person you choose, and there's a record.

In MaintenanceOS your properties, tenants, contractors, work orders, jobs and communications sit in your own organisation's space, kept apart from other organisations' records by isolation controls in the code that are covered by tests.

The government is consulting on how Awaab's Law should apply to private rented homes in England. Nothing is decided yet, and the consultation closes on 18 December 2026. We've summarised what's proposed in our guides.

We won't tell you a tool makes you compliant, because none can. What helps, whatever the final rules say, is knowing when a report arrived, what it said and what happened next. That's what MaintenanceOS is designed to record.

At our 30 September 2026 product checkpoint, all 196 targeted claims-and-safety tests passed, covering explicit transfer, the "never invent" rules, organisation isolation, job lifecycle, decision rules and invoice rules among others. We won't publish uptime figures or reviews we haven't earned. These are targeted, automated tests run against the product code in a controlled test set-up, not on a live service. They show specific rules behaved as designed in testing, not that every rule will hold in every real situation, and voice intake is still under testing.

We're pre-launch. Voice intake is still under testing, and we're taking early-access requests from landlords who want to see how it works. In a demo we'll take you through a sample repair report, from first contact to escalation to clearance, using sample data, and we'll be clear about what's in place now and what's still being built.