Job intake for maintenance firms that won't promise an engineer you haven't sent

• A wasted first visit. The engineer arrives with the wrong parts, because "it's broken" was all anyone wrote down.
• A promise you didn't make. Someone told the caller an engineer was on the way. Now you're either sending one at a loss or explaining why you're not.
• A safety call that sat in a queue. A report that should have gone straight to a supervisor was logged as routine because it was described casually.
• A dispute with no record. The client says they reported it last week. You need to show what was reported, when, and what you said.

It gathers what the engineer needs. The assistant collects the caller's details and turns what they report into a structured repair request, so the job starts with a description someone can work from.

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

Dangerous reports are held for a person, not left in a queue. 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.

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

Done means done. Consequential actions leave audit evidence alongside the job, and the system only reports something as done when there's evidence it succeeded. The rule is that "we've sent an engineer" is only said when there's evidence it happened.

For a contractor, a false promise isn't just awkward. It's a cost. The assistant must not invent a booking or appointment time, a contractor or engineer 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.

MaintenanceOS has no authority to move money either (no client-money authority). Quotes and invoices go through checks, but there's no payment, refund, compensation or fee-waiver execution in the system. Pricing decisions stay with you.

If a caller 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, not to quietly forward the call somewhere unplanned.

Landlords, agents and housing providers who send you work increasingly want to know how reports are handled, especially out of hours. A firm that can explain its intake rules in plain English, and show a record of each job, is easier to trust with a contract. Our published safety rules are written to be shared with clients.

We don't claim that MaintenanceOS makes you or your clients compliant with anything. Their legal duties stay with them, and yours stay with you.

Your properties, residents, contractors, work orders, jobs, communications, exports, action evidence and call records sit in your organisation's own space. Isolation controls in the code keep each organisation's records apart and are covered by tests. Requests from the phone provider are signature-checked.

We don't claim job scheduling, engineer apps, accounting links or a customer portal. In a demo we'll show what's in place now and what's still being built.

At our 30 September 2026 product checkpoint, all 196 targeted claims-and-safety tests passed, including the "never invent" rules, explicit transfer, job lifecycle, decision rules and invoice rules. Local acceptance, including 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 maintenance firms. In a demo we'll take a sample call through intake, escalation and clearance using sample data.