Case Study

How a regional brokerage responds on chat and SMS, books eligible showings, and routes negotiations to an agent.

This multi-agent brokerage serves several metro markets, but no individual agent can respond first at every hour. Kingstone built an AI agent that uses active listing data to answer on chat and SMS, book eligible showings, and hand negotiations to an agent.

ClientAnonymous, name withheld by request
LocationRegional, multiple metro markets
IndustryReal estate
ChannelsWeb chat + SMS

Documented deployment workflow

From listing question to showing or listing-agent handoff

Prospects get answers and can book eligible showings without waiting for an agent, while offers and negotiations stay with the listing team.

01Lead asks on chat or SMS

The conversation may concern a specific active listing or general availability.

02Listing questions are answered

The agent uses listing details such as square footage, HOA fees, and showing availability.

03Eligible showing is booked

When the requested slot and workflow rules allow, the showing is added to the calendar.

04Negotiation goes to the agent

Offers, counters, contingencies, and advice requests are routed to the listing agent.

The brokerage also received a dedicated dashboard to review lead activity, booked showings, handoffs, deployment notes, and the metrics the team tracks.

The challenge

Before launch, inbound listing questions could sit for hours when no agent was immediately available. With dozens of agents working across several markets, the brokerage needed one reliable first-response workflow that could answer routine questions and schedule a showing without waiting for an individual agent to notice the lead.

The solution

Kingstone deployed an AI agent that uses the brokerage's active listing data, including square footage, HOA fees, and showing availability. It can answer on web chat and SMS and book eligible showings for any agent's listing. When a conversation involves an offer, counteroffer, contingency, or request for advice, it routes the lead to the listing agent. The AI does not negotiate or advise on an offer.

The results

Figures below are from inbound chat and SMS leads in the first 90 days of live deployment. Booking share counts only leads that met the brokerage's showing eligibility rules.

Hours → <1 min
First response on chat and SMS

Down from a multi-hour internal baseline before launch.

40%
Eligible leads book a showing with no agent involved

Showings land on the calendar while agents are still with clients or offline.

Deals stay human
Offers, counters, and contingencies never handled by AI

The moment negotiation starts, the listing agent owns the conversation.

Showing already on the calendarBy the time an agent sees the notification, an eligible showing can already be booked.
Chat and SMS, same workflowInbound leads split evenly between web chat and text, depending on how they found the listing.
Listing facts in-flowTwo in three conversations concern a specific active listing — square footage, HOA fees, and showing windows answered from live listing data.

“Leads don't wait for business hours, and now neither do we. The assistant books eligible showings before an agent needs to step in.”

Director of Operations
Multi-agent real estate brokerage

This case study describes a real Kingstone client deployment. The client's name and identifying details have been withheld at its request. Figures shown are from this client's deployment.

See how this workflow could fit your operation.

Book a working session to map listing data, scheduling rules, and the conversations agents should own.

Book a Working Session →