Solution blueprint · Real estate · CRM and AI
A real estate CRM with AI lead qualification on WhatsApp and voice
Leads from 99acres, MagicBricks, Housing, Meta and Google ads land in one pipeline. An AI assistant replies within a minute on WhatsApp, qualifies budget, location and timeline, books the site visit and hands a warm lead to the right salesperson.
Design mockup with sample data. This is a solution blueprint by Infovion Technologies, not a client engagement.
- < 1 min
- designed first response to every lead
- 7
- lead sources in one pipeline
- 8 – 12 weeks
- from kick-off to go-live
- ₹2.5 – 6 lakh
- typical build budget in India
The situation
The problem this solves
A developer with three projects spends several lakh rupees a month on portals and ads. Leads arrive in six inboxes, are copied into a spreadsheet and called back the next day, by which time the buyer has spoken to two other builders. Nobody can tell which source produces bookings rather than enquiries.
The sales head wants every lead answered at once, the unserious ones filtered politely, site visits put straight into calendars, and a weekly number for cost per booking by source.
The system
What it includes
Lead capture from every source
Portal feeds, Meta and Google lead forms, the website, missed calls and walk-ins create a lead with its source and campaign, and duplicates are merged by phone number.
AI qualification on WhatsApp
Within a minute the assistant greets the lead by project, shares the brochure and price sheet, asks budget, configuration, purpose and timeline in a natural chat, and scores the lead.
AI voice follow-up
Leads who do not reply on WhatsApp get a short call from a voice agent in English or Hindi, which says it is an automated assistant and offers a call-back from the sales team.
Site visit scheduling
Free slots from the sales team's calendars, pick-up details, reminders, and visit feedback captured on the salesperson's phone.
Inventory and bookings
Tower, floor and unit availability, price sheets, holds, booking forms, payment schedules linked to construction stages and demand letters.
Channel partners
Broker registration, lead tagging with protection periods, and commission statements.
Sales dashboard
Pipeline by stage and salesperson, response time, visits, bookings, and cost per lead, visit and booking for each source.
How it works
From input to outcome
- 01
Lead in
Portals, ads and the website push leads by API or email parsing.
- 02
First reply
The assistant messages on WhatsApp inside a minute, with a template the buyer has consented to receive.
- 03
Qualify
Budget, configuration, location and timeline are collected and scored.
- 04
Book the visit
A slot is offered and confirmed; the salesperson gets the summary.
- 05
Track to booking
Visits, negotiations, bookings and payments stay on one record.
What the design is built to achieve
- Every lead answered within a minute, including nights and weekends.
- Salespeople spend their time on qualified buyers; the assistant handles first contact and follow-ups.
- Cost per booking by source, so the marketing budget follows results.
- Consent recorded for every WhatsApp and call, with an opt-out honoured at once.
Technology
Next.js, NestJS, PostgreSQL, WhatsApp Cloud API, Claude API, Voice agent (speech-to-text and text-to-speech), Portal and ad lead APIs, React Native / PWA for sales staff
Budget and timeline
| Build, clients in India | ₹2.5 – 6 lakh |
|---|---|
| Build, clients outside India | $3,000 – 7,000 |
Timeline. 8 – 12 weeks: lead capture and WhatsApp qualification first, then inventory, bookings and voice.
Running cost. WhatsApp message charges, voice minutes and model usage, estimated from monthly lead volume.
Indicative planning ranges for 2026. Every project receives its own fixed-price proposal after a first call. Source code and accounts belong to the client.
Request a fixed-price proposalFAQ
Frequently asked questions
What is AI lead qualification?
An AI assistant contacts each new lead immediately, asks the questions a salesperson would ask first, such as budget, requirement and timeline, scores the lead from the answers and passes qualified leads to the sales team with a summary.
Can leads from 99acres, MagicBricks and Housing go directly into the CRM?
Yes. The portals provide lead feeds by API or email, and Meta and Google lead forms connect through their APIs. Each lead is tagged with its source so cost per booking can be measured.
Are AI voice calls to leads allowed in India?
Calls and messages should go only to people who have enquired and consented, should identify the caller, and must respect TRAI's commercial communication rules and do-not-disturb preferences. In this design the voice agent says it is an automated assistant, and consent and opt-outs are stored on the lead.
How much does a custom real estate CRM cost?
A focused CRM with lead capture and follow-up is typically ₹1 lakh to ₹3 lakh. With AI qualification, inventory, bookings and channel partners, as described here, it is typically ₹2.5 lakh to ₹6 lakh.
Is this a project you delivered for a client?
No. This page is a solution blueprint, shown with sample data. It applies equally to developers and brokerages in India and the Gulf.
More blueprints
Other systems we have designed
Looking for delivered work? Read the case studies on our school ERP, jewellery software and website.
Planning a system like this?
Tell us how the work is done today. We reply within one business day with questions, an approach and a fixed-price proposal where the scope allows.