Repair reports your landlords can trust, and your team doesn't have to chase

Ask anyone who has run a repairs line: the trouble is rarely the repair itself.

• The report arrives thin. No property reference, no description that a contractor can work from, no sense of whether it's getting worse.
• Urgency depends on who answered. One negotiator escalates a damp patch, another leaves a hissing boiler till morning.
• Promises leak out. "We'll have someone there tomorrow" is said to calm a tenant, before anyone has checked with the landlord or a contractor.
• The trail goes cold. When a landlord asks what was reported and when, the answer is spread across inboxes, call notes and memories.

Each of these costs you time, and some of them cost you landlords.

Consistent capture. The assistant collects the caller's details and turns what they report into a structured repair request, the same way every time.

Rules decide, not the AI. Safety, the progress of a job and approvals are decided by fixed rules on our server. The AI can't override them.

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

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

Evidence, not assertion. Consequential actions leave audit evidence alongside the job, and the system only reports something as done when there's evidence it succeeded.

Because you carry the blame for both sides. The assistant must not invent a booking or appointment time, a contractor dispatch, a refund, compensation, a waived fee, account information or a safety reassurance. If nothing has been arranged, it won't say it has. Not a live always-on phone.

That protects your relationship with the tenant, who isn't told something false, and with the landlord, who isn't committed to a cost or a visit they haven't agreed. MaintenanceOS has no authority to move money at all (no client-money authority): quotes and invoices are checked, but there's no payment, refund or compensation in the system.

If a tenant asks for a person, they can ask to be transferred (live transfer handling is still under testing). If something fails technically, the system is built to fail safe rather than pass the call somewhere unplanned.

MaintenanceOS is built for many organisations on one system. Your agency's properties, residents, contractors, work orders, jobs, communications, exports, action evidence and call records sit in your organisation's own space. Isolation controls are in the code and covered by tests, and requests from the phone provider are signature-checked so that fake ones are designed to be rejected.

What we don't claim yet: per-landlord rule sets, landlord logins or a customer portal. In a demo we'll show you what's in place now and what's still being built.

The government is consulting on how Awaab's Law should apply to private rented homes in England. The consultation notes that where agents manage repairs, the landlord "would remain ultimately liable" and "may need to establish new contractual agreements with their agent". Nothing is decided, and the consultation closes on 18 December 2026.

It's a good moment to review how repair reports reach you out of hours, how quickly they're logged, and who decides what's urgent. No tool makes an agency or a landlord compliant, and we won't suggest otherwise.

At our 30 September 2026 product checkpoint, all 196 targeted claims-and-safety tests passed, including explicit transfer, the "never invent" rules, organisation isolation, job lifecycle, decision rules and invoice rules. Local acceptance, including a full test pass and backup and restore, was evidenced on 10 September 2026. 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 agencies. In a demo we'll walk a sample tenant report through intake, escalation and clearance using sample data.