PROPERTY & FM · SYSTEM

When the managing agent's inbox becomes the whole job

IN SHORT

Most of the inbox is people asking what is happening with something already logged — a question the system can answer perfectly and a human is currently answering badly. Clearing that majority is what gives managers time for the complaints that matter.

What actually goes wrong

One inbox carries repair reports, complaints, consent requests, solicitor enquiries, arrears queries and service charge disputes, and every message is urgent to whoever sent it. Managers triage by scrolling. The complicated items get opened and reclosed several times before anyone has an hour to deal with them, and the simple status questions — the clear majority — queue behind them for days, generating a second and third chase each.

What it costs

Complaints, mostly. In this sector complaints are rarely about the repair itself; they are about the silence before the repair. Every day a reasonable question goes unanswered converts a neutral resident into an angry one, and an angry resident costs a manager an hour rather than a minute.

How the fix works

Every message is read and classified within minutes. Status questions about existing jobs are answered from the live record with a real update — what was raised, who is attending, when. Repair reports go into triage and become jobs. Complaints, consents, legal and arrears matters are routed to the responsible manager with the property record and correspondence history attached. Complaint and vulnerability indicators escalate by hard rule, and anything the classifier is unsure about goes to a person unanswered.

What stays with your people

Every complaint, consent, arrears conversation and anything involving a vulnerable resident or a lease consequence. The point of clearing the routine volume is to make those properly answerable.

What you get

  • Every message read and classified within minutes of arrival
  • Routine status questions answered accurately from live job data
  • Complaints and vulnerability indicators escalated by hard rule
  • Property, tenancy and history attached before a manager opens it
  • A route to a person on every automated reply, stated plainly

Questions we get asked

Will residents be answered by a bot pretending to be staff?
No. Automated updates say clearly that they are automatic, what has been logged, what happens next and how to reach a person. We do not build systems that impersonate a named member of staff.
What if it answers something it should not have?
It only auto-replies on the categories you approve, and those are deliberately narrow at the start — usually status updates on existing jobs. Everything else is prepared for a manager to send, which is still most of the time saving.
How long before the inbox actually feels different?
Four to six weeks for a first version on your highest-volume categories. The measurable change is usually in average first-response time, which moves within the first fortnight of go-live.

TRUST & CREDENTIALS

How we work, and what stands behind it

This page is maintained by Forth Systems. Everything listed below describes our own team, hosting choices and the technologies we build on — it is a statement of practice, not an independent certification or an endorsement by the vendors named.

UK team & data residency

Who builds it, and where your data sits while they do.

  • UK-based engineers

    Edinburgh-headquartered. Every system is designed, built and supported by our own UK-based engineering team — no offshore delivery pool.

  • UK / EU hosting by default

    Applications and databases are provisioned in UK or EU regions unless you require otherwise, with encryption in transit and at rest.

  • Human-in-the-loop by design

    Every AI system we ship keeps a manual override. Nothing irreversible happens without an operator able to review, edit or stop it.

  • Audit trails as standard

    Automated actions are written as first-class records — who or what did it, when, against which input — so operations stay evidence-ready.

Systems we build on

The platforms our systems run on. These are the technologies we deploy and support — not sponsorships or reseller badges.

  • OpenAI, Anthropic & Google models

    Model-agnostic delivery. We route each workload to the model that fits it on cost, latency and accuracy, and can switch without a rebuild.

  • Supabase & Postgres

    Row-level-security Postgres as the operational spine under every platform we run.

  • Stripe payments

    Payment capture, checkout and reconciliation wired directly into job and permit workflows.

  • Xero, Sage & HubSpot integrations

    Production integrations into the finance and CRM systems UK operators already run, so automation lands where the business keeps its records.

Streetworks & industry credentials

Operational domains we build in daily, with the sector systems we integrate against.

  • DfT Street Manager integration

    The permit chain we built for Kerbco creates and tracks streetworks permit applications against DfT Street Manager and local highway authority processes.

  • NRSWA-aligned workflows

    Permit, reinstatement and traffic-management workflows built to the New Roads and Street Works Act process contractors are inspected against.

  • Traffic management planning

    Roadplan produces signing and guarding layouts for council submission and for the crew installing them on site.

  • Operator-built, not consultancy-built

    Our platforms are built around real operating workflows — including the permit chain we built for our client Kerbco, a Scottish drop kerb contractor.

Insurance certificates, registration numbers and security documentation are available on request — ask the team.