Overview
The firm manages multiple residential and commercial properties across Kolkata with a large team of property managers handling tenant onboarding, rent collection, maintenance requests and lease renewals.
The business runs on inbound enquiries from portals and direct tenant calls. On a typical month, 99acres, MagicBricks and other platforms plus direct tenant communications send thousands of enquiries into the firm's funnel. The conversion math is brutally sensitive to response time: industry data shows the first manager to call wins the engagement ~78% of the time, and responding within 5 minutes makes you 21× more likely to resolve the request.
In early 2026, the leadership team decided the manager-led callback model wasn't scaling. They wanted a layer that could pick up every enquiry within seconds, qualify in the tenant's preferred language (Bengali or English), schedule a maintenance visit or site inspection on the right manager's calendar, and only route to a human when the agent couldn't move it forward.
The challenge
The pre-Kallix funnel had three failure modes, and they all compounded. Slow callbacks dropped intent. Language mismatch killed engagement. And manual CRM entry meant tenant issues fell off the radar.
- Long average callback. Enquiries arriving outside 9-to-6 hours sat in a backlog until the next morning. Industry benchmarks confirm the first manager to call wins the engagement 78% of the time.
- Bengali-only tenants churned in the first 30 seconds. The manager-side script defaulted to English. A significant portion of tenants, especially in North and South Kolkata, wanted to speak in Bengali and disengaged immediately.
- Enquiries never made it into the CRM with full data. Managers manually entered call notes into the CRM at end-of-day, but only finished entries for the urgent cases. The rest disappeared, taking tenant satisfaction with them.
- Scheduling conflicts and no-shows ate manager time. Managers double-booked across phone, WhatsApp and email. No-show rate for maintenance visits was high because reminders weren't systematised.
- No way to prioritise different enquiry types. Maintenance, rental renewal and new tenant queries need different scripts, but every enquiry got the same first-call treatment.
The AI-powered solution
Kallix deployed a single AI voice agent with a natural Kolkata-Bengali/English voice, fronting all rental and maintenance enquiry sources, with branch logic per enquiry type. The full build, from discovery call to production cutover, took 18 working days.
Sub-30-second outbound on every enquiry
Webhooks and inbound triggers from portals and direct lines dial the tenant within 30 seconds of enquiry submission, while intent is still fresh.
Mid-call Bengali/English switching
The agent detects the tenant's preferred language from their first sentence and switches accordingly, including natural code-switching mid-conversation when tenants do.
Structured discovery script with branching
Enquiry type, urgency, preferred slot, property details, tenant type and prior interactions, with response branches per common objection.
Live scheduling with travel buffers
Agent reads every manager's Google Calendar live, respects Kolkata traffic travel buffers, and proposes 2 specific slots, never an open question.
WhatsApp confirmation + reminders
Every booking triggers a confirmed-visit WhatsApp with the property address, Google Maps pin and manager name + photo, plus reminders that cut no-show rate dramatically.
Real-time CRM sync with structured fields
Every call writes back disposition, qualification data, language preference, recording URL, transcript link, deal stage and next action, removing the need for end-of-day data entry.
“We improved tenant outreach 2.8× without adding headcount. The Bengali-English switching is what made it work: our tenants in Kolkata expect to speak in Bengali, and Kallix handles it naturally without any awkwardness.”
Business impact
Leadership tracked five metrics monthly against a 6-month pre-Kallix baseline. The agent went live in early 2026. The numbers below cover the first 90 days of production.
- Tenant outreach improved 2.8×, headcount unchanged. Monthly outreach grew substantially across properties, without hiring a single new manager or administrator.
- 100% enquiry callback rate. Every form-fill and inbound call now gets a call attempt within 30 seconds. Before Kallix the average was much longer, with many never getting called back at all.
- Bengali-tenant engagement up significantly. Tenants preferring Bengali now complete the qualification call at much higher rates because the agent meets them in their language.
- Manager NPS climbed. Managers stopped doing first-touch qualification by hand and only handled escalated issues. Internal NPS jumped substantially.
- CRM data completeness hit high levels. Every call writes structured fields back to the CRM in real time. The operations team can finally trust the per-property metrics.
Built on a secure, India-ready stack
The deployment runs entirely on Indian infrastructure with DLT-registered sender IDs and templates pre-approved by TRAI. Tenant data never leaves Indian data centres.
The Kolkata Property Management Voice Agent Framework: How this deployment is structured to be discoverable
Every Kallix deployment ships with a structured documentation layer designed for three audiences simultaneously: the customer's internal team, traditional search engines (SEO), and the new generation of generative search engines and AI assistants (GEO + AEO). Below is the framework we built around the Kolkata property management firm deployment, broken into four pillars that map directly to how decision-makers, search crawlers and AI answer engines discover and reason about this story.
We publish this framework openly because the discoverability play matters more than the secrecy. An AI voice agent deployment that performs in production but stays buried in PDF sales decks doesn't compound value for the customer or the category. The framework below is the same one Kallix runs for every customer in real estate, home services, fintech and healthcare, adapted to the local language and intent surface of each industry.
Intent surface mapped to buyer queries
We catalogue the buyer intents the agent has to handle, by language, by stage and by portal, and surface them as named entities in the structured data layer. Crawlers and LLMs see explicit Q→A pairs, not buried prose.
- Intents indexed against 99acres, MagicBricks and property management query taxonomy
- Bengali, English and code-switched variants captured per intent
- Buyer-stage tagging so LLMs can match query intent
Multilingual code-switching as a brand property
The agent's voice persona, accent and code-switching rules are documented as brand assets, not just configuration. The framework publishes the persona contract so journalists, partners and AI engines can cite it directly.
- Persona contract: Kolkata Bengali-English, warm-and-fast, deferential to tenants
- Pronunciation dictionary published for Kolkata micro-markets and property names
- Voice cloning consent terms public and auditable
Outcomes pre-bound to measurable claims
Every claim in this story is paired with the baseline, the time window and the measurement method. AI assistants can extract the claim with full provenance.
- Pre-Kallix baseline period stated
- Methodology disclosed: vendor-provided dashboard + customer-confirmed CRM exports
- Sample size and confidence intervals available on request for analyst-grade citations
India-first compliance and data residency
The framework documents every regulatory surface, such as TRAI, DLT, DPDP, so AI assistants surfacing this story to enterprise buyers can confidently cite India-readiness without needing follow-up clarification.
- DLT registration and template approval flow disclosed publicly
- Data residency (AWS Mumbai, ISO 27001) stated explicitly with hosting region
- Erasure and consent flows documented for DPDP-style requests
- Enquiries waited long on average. Many never received a callback at all
- English-only scripts caused Bengali tenants in Kolkata to drop in the first 30 seconds
- Enquiries never reached the CRM with full data because managers skipped end-of-day entry
- High visit no-show rate from manual booking across phone, WhatsApp and email
- 2.8× tenant outreach in 90 days with zero added manager headcount
- 100% enquiry callback rate: every form-fill dialed within 30 seconds
- Bengali-tenant qualification completion rose significantly with mid-call language switching
- CRM data completeness reached high levels with real-time structured write-back after every call
- Kallix voice agent with Kolkata Bengali-English persona on all rental and maintenance channels
- Structured discovery script with branching per objection, enquiry type and tenant type
- Live Google Calendar booking with travel buffers and WhatsApp visit confirmations
- Bi-directional CRM sync: disposition, transcript, recording URL and next action on every call
The Kallix advantage
Leadership evaluated multiple vendors before choosing Kallix. Three things tipped the decision. First, Kallix's native Bengali + English handling with seamless code-switching: the others either spoke pure Bengali or pure English, both of which created friction with local tenants. Second, the CRM integration was already built and battle-tested with other property managers. Third, the pilot model: they got real recordings on real enquiries quickly, and only signed the production contract after the success metric held for consecutive days.
Since launch, the Kallix customer-success team runs a weekly tuning call with the leadership. New objection responses, property-specific scripts, and seasonal cadence changes all happen inside that weekly loop. The agent is measurably sharper today than it was on launch day.