Engagement

Property and real estate

Enquiries answered at the hour they arrive, and listings that agree with each other.

Home
Engagements
Property and real estate

Web · AI

Property and real estate

Property enquiries arrive in the evening, at weekends and in two languages, and they go cold quickly. Most brokerages lose more deals to response time than to price.

Judged on

Time to first replyMedian and 90th percentile, split by hour of day and by language.
Share of enquiries workedOf everything that arrived, how much got a real response.
Viewings bookedFrom the same enquiry volume, so it is a conversion measure rather than a demand one.
Escalation accuracyHow often the agent correctly handed over, and how often it should have.

The pattern

What we keep
walking into.

Listings live in a CRM, on two or three portals and on the website, and within a week of any change the four disagree.
Enquiries land in a shared inbox that nobody owns after 18:00 — which is when a large share of them arrive.
Arabic enquiries wait longer than English ones, because fewer people are available to answer them.
Viewings are booked by phone tag rather than against real calendar availability.
Nobody can say what proportion of enquiries were actually worked. Only how many arrived.

The approach

What we do
about it.

One source for listings

One system becomes the source of truth and everything else reads from it — website, portals, brochures. A price change is made once.
A site that sells the listing

Fast, bilingual, with genuine right-to-left Arabic rather than a mirrored stylesheet. Listing pages carry structured data so portals and search engines read them correctly.
Instrument the enquiry path before automating it

We measure what happens now: how many enquiries, at what hour, in which language, answered how quickly. That measurement is what decides whether an agent is worth building.
Then an agent, if the numbers justify one

A viewings and enquiries agent that answers out of hours and books against real availability. It never discusses price, contracts or negotiation — those escalate to a person with a written summary.

Shape of the work

Timeline, team
and starting point.

	Detail
Where it usually starts	A Site Health Audit on the current site, or an AI Opportunity Audit across the enquiry workflow.
Typical build	Bilingual listings site: eight to twelve weeks.
Typical pilot	One agent, four to six weeks, fixed price, against one agreed metric.
Who works on it	Strategist, designer, two developers, an AI engineer. The Dubai pod leads, London covers the late shift.

Packages

Where this
usually starts.

Package	Model	From
Launch Site + AssistantA marketing site plus one grounded site assistant, live in weeks	Fixed scope	from £4,500
AI Opportunity AuditTwo to three weeks, ending in 5–10 ranked and costed use cases	Fixed price	£6,500
Agent PilotOne agent, four to six weeks, against one agreed metric	Fixed price per agent	from £9,000