Softpiper Solutions

Real estate · Customer conversations

Lead qualification and property-matching concierge

Qualify portal and ad leads on web and WhatsApp, match them to live inventory, answer neighbourhood questions and book site visits, with Claude and Gemini.

  • ClaudeAnthropic
  • GeminiGoogle
  • Typical timeline: 4–10 weeks

The problem

Portals and ads bring high lead volumes, follow-up is slow, and agents spend their time on enquiries that were never going to buy.

  • Leads go cold while they wait for a callback.
  • Agents re-ask the same budget, location and timeline questions.
  • Neighbourhood and commute questions take research time.

How we solve it

A concierge that qualifies each lead on budget, location, timeline and financing, matches live listings, answers area questions from Google Maps data and books site visits into your agents' calendars.

It plugs into HubSpot or Zoho CRM, Salesforce, Listings database, WhatsApp Business and Google Calendar, so nothing you rely on today is replaced. The architecture below shows each step and which model does the work.

Architecture

From your stack, through the AI layer, to numbers you can track

Each step names the model or system doing the work. Writes to your systems wait for a person to approve them.
Lead qualification and property-matching concierge. Your systems (HubSpot or Zoho CRM, Salesforce, Listings database, WhatsApp Business and Google Calendar) connect to Softpiper's AI layer, which runs these steps: Instant first reply (WhatsApp Cloud API · CRM); Qualify (Claude Sonnet); Match listings (Inventory tool); Answer area questions (Grounding with Google Maps); Voice callback (optional) (Gemini Live API); Book and hand off (Google Calendar · HubSpot / Zoho MCP). Outcomes are measured as speed to lead, share of leads qualified automatically, site-visit booking rate and agent hours saved.

Your stack

  • HubSpot or Zoho CRM
  • Salesforce
  • Listings database
  • WhatsApp Business
  • Google Calendar

AI layer

Softpiper AI layer

  • Claude
  • Gemini
  1. Instant first reply, using WhatsApp Cloud API · CRM

    Leads from portals, ads and your site land in the CRM and get a reply on WhatsApp or web chat within moments.

  2. Qualify, using Claude Sonnet

    The concierge asks about budget, location, timeline and financing, and records the answers as structured fields.

  3. Match listings, using Inventory tool

    Listings are searched through a tool over your inventory database and shared with photos and links.

  4. Answer area questions, using Grounding with Google Maps

    Neighbourhood, school and commute questions are grounded in Google Maps.

  5. Voice callback (optional), using Gemini Live API

    Leads who ask for a call get one from a voice agent that can check listings and book a visit.

  6. Book and hand off, using Google Calendar · HubSpot / Zoho MCP

    Site visits are booked on the right agent's calendar, and the conversation is written to the CRM.

Outcomes you measure

  • Speed to lead
  • Share of leads qualified automatically
  • Site-visit booking rate
  • Agent hours saved

Why this model

Claude and Gemini, each where it leads

We choose per task on capability, cost and where your data must stay. Final versions are picked at kickoff.
ClaudeAnthropic

Claude runs the qualifying conversation and uses tools to search your inventory and book visits, following the fair-housing and no-advice policies written into its instructions.

GeminiGoogle

Grounding with Google Maps answers neighbourhood and commute questions from live map data. For leads who prefer a call, the Gemini Live API runs a voice callback agent with function calling in 70 languages.

Delivery

What you get, how long it takes, and how we keep it safe

Guardrails

  • Fair-housing and anti-discrimination rules are part of the agent's instructions and its evaluation set.
  • No legal, tax or financing advice; those questions go to a person.
  • Calls are recorded only with consent, and the agent says it is an AI.
  • Prices and availability come from your inventory, never from the model.

Plus the guardrails on every build: facts from your systems, approvals for writes and money, a human one step away, audit logs and evals. See all

Deliverables

  • Qualifying concierge on web and WhatsApp
  • Inventory search and visit-booking tools
  • CRM write-back with qualification fields
  • Optional voice callback agent
  • Speed-to-lead dashboard

Typical timeline

  1. Chat, matching and CRM4–6 weeks
  2. Voice callback agent+3–4 weeks

A planning range for a first production release. We confirm scope, price and dates in a tailored proposal.

KPIs to track

  • Speed to lead
  • Share of leads qualified automatically
  • Site-visit booking rate
  • Agent hours saved
  • Lead-to-visit and visit-to-booking conversion

Goals we agree with you and measure from a baseline. They are what we track, not results we promise.

Related services

The services behind this playbook

More playbooks

Related playbooks

All playbooks

Pip · Softpiper's AI

Ask Pip about this playbook

Ask Pip how this would work for you

Pip is Softpiper's AI. Tell it what you run today and it will walk through how this playbook fits, what we would build first and a tailored price range. Or book a call with the team.

Book a call