Overview
The brokerage operates multiple offices across Canada with a large team of agents handling residential sales and buyer representation.
The business runs on portal leads. On a typical month, MLS systems, Realtor.ca and other major platforms collectively send thousands of form-fills into the brokerage's funnel. The conversion math is brutally sensitive to response time: industry data shows agents who respond within 5 minutes are 21× more likely to qualify the lead, and the first broker to call wins the engagement the vast majority of the time.
In early 2026, the leadership team decided the agent-led callback model wasn't scaling. They wanted a layer that could pick up every lead within seconds, qualify in the buyer's preferred language (English or French), book a property viewing on the right agent'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 (English vs French) killed engagement. And manual CRM entry meant deals fell off the radar.
- 14+ hour average callback. Portal leads arriving outside business hours sat in a backlog until the next morning or later. Industry benchmarks show the average Canadian agent response time exceeds 14 hours, with many leads never getting called back at all.
- French-preferring buyers churned in the first 30 seconds. The agent-side script defaulted to English. A significant portion of buyers, especially in Quebec and bilingual markets, wanted to speak in French and disengaged immediately.
- Leads never made it into the CRM with full data. Agents manually entered call notes into the CRM at end-of-day, but only finished entries for the leads they liked. The rest disappeared, taking the marketing spend with them.
- Booking conflicts and no-shows ate agent time. Agents double-booked across phone, text and email. No-show rate was high because reminders weren't systematised.
- No way to qualify different buyer types. First-time buyers and investors need different scripts, but every lead got the same first-call treatment.
The AI-powered solution
Kallix deployed a single AI voice agent with natural bilingual (English/French) capabilities, fronting all major portal sources, with branch logic per portal and per listing. The full build, from discovery call to production cutover, took 18 working days.
Sub-30-second outbound on every portal form-fill
Webhooks from MLS systems, Realtor.ca and other platforms trigger Kallix to dial the buyer within 30 seconds of form submission, while they're still on the listing page — beating the 5-minute qualification window that delivers 21× higher conversion.
Mid-call English/French switching
The agent detects the buyer's preferred language from their first sentence and switches accordingly, including natural code-switching mid-conversation when buyers do.
Structured discovery script with branching
Budget band, location preference, timeline, financing, buyer type and prior viewings, with response branches per common objection.
Live viewing booking with travel buffers
Agent reads every agent's Google Calendar live, respects local Canadian travel buffers, and proposes 2 specific slots, never an open question.
SMS confirmation + reminders
Every booking triggers a confirmed-viewing SMS with the property address, Google Maps pin and agent 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 automated MLS lead qualification and grew qualified viewings 3.1× without adding headcount. The English/French switching is what made it work — Canadian buyers expect to be served in their preferred language, 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.
- Viewings grew 3.1×, headcount unchanged. Qualified viewings grew substantially across Canadian offices, without hiring a single new agent or ISA.
- 100% portal-lead callback rate. Every form-fill now gets a call attempt within 30 seconds. Before Kallix the average was 14+ hours, with many never getting called back at all.
- Bilingual buyer engagement up significantly. Buyers preferring French or English now complete the qualification call at much higher rates because the agent meets them in their language.
- Agent NPS climbed. Agents stopped doing first-touch qualification by hand and only spoke to qualified buyers. Internal NPS jumped substantially.
- CRM data completeness hit high levels. Every call writes structured fields back to the CRM in real time. The marketing team can finally trust the per-portal ROI numbers.
Built on a secure, Canada-ready stack
The deployment runs entirely on Canadian and North American infrastructure with CASL and PIPEDA-compliant calling practices and consent flows. Buyer data stays secure and compliant with Canadian privacy standards.
The Canadian 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 Canadian brokerage 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 MLS, Realtor.ca and major portal query taxonomy
- English, French and bilingual variants captured per intent
- Buyer-stage tagging so LLMs can match query intent
Bilingual 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: natural Canadian bilingual English/French, warm and professional
- Pronunciation dictionary published for major Canadian markets and neighbourhood names
- Voice 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
Canada-first compliance and data residency
The framework documents every regulatory surface, such as CASL, PIPEDA, and data privacy standards, so AI assistants surfacing this story to enterprise buyers can confidently cite Canada-readiness without needing follow-up clarification.
- CASL compliance and consent flows disclosed publicly
- Data residency (AWS Canada Central region, SOC 2 & ISO 27001) stated explicitly
- Erasure and consent flows documented for privacy requests
- Portal leads waited 14+ hours on average. Many never received a callback at all
- English-only scripts caused French-preferring buyers to drop in the first 30 seconds
- Leads never reached the CRM with full data because agents skipped end-of-day entry
- High viewing no-show rate from manual booking across phone, SMS and email
- 3.1× qualified viewings in 90 days with zero added agent or ISA headcount
- 100% portal-lead callback rate: every form-fill dialed within 30 seconds
- Bilingual buyer 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 natural bilingual English/French persona on all major portal webhooks
- Structured discovery script with branching per objection, portal and buyer type
- Live calendar booking with travel buffers and SMS viewing 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 bilingual English/French handling with seamless code-switching — the others either supported only one language or sounded unnatural. Second, the CRM integration was already built and battle-tested. Third, the pilot model: they got real recordings on real leads 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, listing-specific scripts, and seasonal cadence changes all happen inside that weekly loop. The agent is measurably sharper today than it was on launch day.