Enquiry to viewing

Answer every property enquiry while the buyer is still interested

Property enquiries arrive at 9pm on a portal, a WhatsApp number, and a web form — and decay fast, because the buyer is messaging three agencies at once. This blueprint responds immediately with listing-aware answers, qualifies on the criteria your agents actually care about, books the viewing against real diaries, and hands over a brief instead of a name and number.

AI WORKERSORCHESTRATED PROCESSHUMAN AUTHORITY4 roles, trust-scoped6 stages, each with an owner1 decision ownerEnquiry workerQualification workerViewing coordinatorNurture worker1CaptureEnquiry worker2Answer from sou…Enquiry worker3QualifyQualification wor…4MatchQualification wor…5Book or nurtureViewing coordinat…6Hand overViewing coordinat…Licensed agentCONTROLS AROUND EVERY STAGE4 guardrails · 4 decision rules · 5 channels · tamper-evident audit
The blueprint at a glance — worker roles feed the orchestrated stages, and the dashed paths are the escalations into human authority.
The team
4 AI worker roles escalating into 1 human decision owner.
The process
6 orchestrated stages, each with a named decision owner.
The channels
WhatsApp, Voice, Web chat, SMS, Email on one shared context.

The shift

What breaks today, and what changes

The challenge

  • High-intent enquiries land outside working hours and are answered when the buyer has already booked elsewhere.
  • Qualification quality depends on who picks up, so agents inherit leads without budget, timing, or funding context.
  • Enquiries spread across portals, WhatsApp, and web forms with no shared history or single follow-up owner.

What changes

  • Every enquiry gets a substantive, listing-aware reply within moments, on the channel it arrived on.
  • Budget, timing, location, and funding position are captured consistently before an agent invests time.
  • Viewings are booked directly against agent availability, with the qualification brief attached.

The team

Every seat has one job and a defined level of autonomy

This is what gets configured in Team Canvas: role-scoped AI workers, the humans they escalate into, and a trust level on each connection that sets what a worker may do on its own. Trust starts tight and widens on evidence.

AI workers

  • Enquiry worker

    Replies immediately with grounded answers about the specific listing.

    Owns
    First response
    Trust level
    Acts within policy — approved listing facts only, no negotiation
  • Qualification worker

    Captures budget, timeline, location preference, and funding position conversationally.

    Owns
    Qualification record
    Trust level
    Acts within policy — captures, never scores out a lead alone
  • Viewing coordinator

    Matches live inventory to the brief and books against real agent availability.

    Owns
    Viewing conversion
    Trust level
    Acts within policy — books only into permitted diary slots
  • Nurture worker

    Keeps not-yet-ready buyers engaged with relevant new inventory.

    Owns
    Follow-up cadence
    Trust level
    Acts within policy — consent-bound, frequency-capped

Human decision owners

  • Licensed agent

    Owns valuation, negotiation, legal questions, and the client relationship.

    Owns: All licensed advice and negotiation

The process

The conversation starts the work. The workflow finishes it.

Each stage records the decision that was made and the role accountable for it — which is what makes the run reviewable afterwards rather than a black box. Where the platform executes a stage rather than a person or agent performing it, that is named too, and accountability still sits with the role.

  1. 1

    Capture

    Is this listing-specific or an exploratory search?

    Enquiry worker

  2. 2

    Answer from source

    Is this fact in the approved listing record? If not, it is not stated.

    Enquiry worker

  3. 3

    Qualify

    Budget, timing, location, funding — and what is still unknown?

    Qualification worker

  4. 4

    Match

    Which live inventory actually fits this brief?

    Qualification worker

    Run by integration

  5. 5

    Book or nurture

    Ready to view now, or into a consent-bound nurture sequence?

    Viewing coordinator

  6. 6

    Hand over

    Which agent, and what does the brief need to contain before they arrive?

    Viewing coordinator

    Run by workflow

Decision rules

The non-negotiables encoded in the workflow, not left to a prompt.

  • Availability, pricing, and property facts come only from the approved listing record — never inferred.
  • Valuation, negotiation, legal, and investment questions route to a licensed agent.
  • High intent or dissatisfaction escalates immediately with the full conversation.
  • Nurture cadence is consent-bound and frequency-capped per contact.

Controls & guardrails

What makes this safe to run in production, and provable afterwards.

  • Approved listing facts as the only source for availability and price.
  • Clear AI disclosure at the start of every conversation.
  • Licensed-agent takeover for advice, negotiation, and legal questions.
  • Consent capture and frequency caps on all nurture messaging.

Platform capabilities

What this blueprint runs on

Nothing here is bespoke. Each blueprint is a configuration of the same platform, which is why the second one you launch reuses the governance you already reviewed.

Channels

  • WhatsApp
  • Voice
  • Web chat
  • SMS
  • Email

Systems it reads and writes

  • Property CRM
  • Listing & inventory feed
  • Portal lead feeds
  • Agent calendars

Measurement

What we instrument from day one

These are the measurements the pilot puts in place, not benchmark results. You set the targets against your own baseline — and the same instrumentation is what decides whether a worker's trust level widens.

Speed to first reply

Per channel

Measured per channel and per hour of day, because the after-hours gap is usually where the pipeline is actually lost.
Enquiry-to-viewing rate

By source

Tracks conversion by portal and campaign so spend can move toward the sources that produce viewings, not clicks.
Brief completeness

Fields at handoff

Measures how much qualification context an agent receives, which is what determines whether the viewing is worth their time.

Rollout

How this one goes live

A deliberately narrow start, supervised, with autonomy widened per role once the record supports it.

  1. Weeks 1–2

    After-hours first response

    Cover the hours you currently miss on one channel. Immediate grounded replies and qualification capture, with handoff to the agent next morning.

  2. Weeks 3–4

    Add viewing booking

    Connect agent diaries and let the coordinator book viewings directly against real availability, with the brief attached.

  3. Week 5+

    All channels plus nurture

    Extend to every enquiry source with shared context, and switch on consent-bound nurture for buyers who are not ready yet.

Questions we get asked

Enquiry to viewing, in practice

Will it give out prices or negotiate?
It quotes only what is in your approved listing record and does not negotiate at all. Valuation, offers, and negotiation route to a licensed agent, because those are the conversations where being wrong is expensive and, in many markets, regulated.
Do buyers know they are talking to an AI worker?
Yes — AI disclosure is part of the conversation opening by configuration. The point of the blueprint is a fast, useful first response, not pretending to be an agent.
How does it handle a lead who is not ready to buy?
The qualification record captures where they actually are, and a nurture worker keeps them engaged with relevant new inventory under consent rules and frequency caps — so the lead stays warm without an agent manually working a follow-up list.

What changes in Real estate

After-hours enquiries get an immediate listing-aware conversation, and licensed advice stays with the agent.

Read the full Real estate analysis

Related blueprints

Next step

Build this team around one measurable win.

We map your version of this process, compose the worker roles, connect your systems, and agree the escalation points with the people who own them — then run it supervised.