Customer Story · Real Estate

How a leading Swedish real estate agency lifted site visits

A leading Swedish real estate agency replaced its missed-call backlog with a Kallix AI voice agent that answers every Hemnet + Blocket enquiry in Swedish or English, books the property viewing and pushes everything to the CRM in under 30 seconds.

3.0×
qualified site visits / month
vs the 6 months before Kallix
48%
more leads recovered
from portals after hours
<30s
speed-to-call
from form-fill to dial
Industry
Real Estate
Company size
Large agency · multiple locations
Region
Sweden
The 30-second version

A leading Swedish real estate agency was losing Hemnet and Blocket leads to slow callbacks (average 15+ hours) and missed after-hours calls. They deployed Kallix in under 3 weeks. Within 90 days, qualified site visits grew 3.0×, after-hours lead recovery jumped 48%, Swedish-buyer engagement improved significantly, and agents stopped doing first-touch qualification by hand.

Background

Overview

The agency operates multiple offices across Sweden with a large team of real estate agents handling residential sales and buyer representation.

The business runs on portal leads. On a typical month, Hemnet, Blocket and other major platforms collectively send thousands of form-fills into the agency'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 agency 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 (Swedish or English), book a property viewing on the right agent's calendar, and only route to a human when the agent couldn't move it forward.

What was breaking

The challenge

The pre-Kallix funnel had three failure modes, and they all compounded. Slow callbacks dropped intent. Language mismatch (Swedish vs English) killed engagement. And manual CRM entry meant deals fell off the radar.

Key pain points
  • 15+ hour average callback. Portal leads arriving outside business hours sat in a backlog until the next morning or later. Industry benchmarks show the average Swedish agent response time exceeds 15 hours, with many leads never getting called back at all.
  • Swedish-only buyers churned in the first 30 seconds. The agent-side script defaulted to English. A significant portion of buyers, especially in regional markets, wanted to speak in Swedish 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, email and WhatsApp. 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.
What we built

The AI-powered solution

Kallix deployed a single AI voice agent with natural bilingual (Swedish/English) 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.

Element 1

Sub-30-second outbound on every portal form-fill

Webhooks from Hemnet, Blocket 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.

Element 2

Mid-call Swedish/English 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.

Element 3

Structured discovery script with branching

Budget band, location preference, timeline, financing, buyer type and prior viewings, with response branches per common objection.

Element 4

Live viewing booking with travel buffers

Agent reads every agent's Google Calendar live, respects local Swedish travel buffers, and proposes 2 specific slots, never an open question.

Element 5

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.

Element 6

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.

IntegrationsHemnetBlocketCRMGoogle WorkspaceTwilio telephonySMS Business API
We lifted site visits 3.0× without adding headcount. The Swedish-English switching is what made it work: buyers in Sweden expect to be served in their preferred language, and Kallix handles it naturally without any awkwardness.
AL
Anna Lindström
COO, Swedish Real Estate Agency
What changed in 90 days

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.

3.0×
Qualified site visits
vs 6-month baseline
48%
After-hours leads recovered
now zero missed
<14%
Viewing no-show rate
down significantly
SEK 0
Added headcount
to handle 3× volume
Key outcomes
  • Site visits lifted 3.0×, headcount unchanged. Qualified site visits grew substantially across Swedish offices, without hiring a single new agent or administrator.
  • 100% portal-lead callback rate. Every form-fill now gets a call attempt within 30 seconds. Before Kallix the average was 15+ hours, with many never getting called back at all.
  • Swedish-buyer engagement up significantly. Buyers preferring Swedish 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.
Architecture

Built on a secure, Sweden-ready stack

The deployment runs entirely on European infrastructure with GDPR-compliant calling practices and consent flows. Buyer data stays secure and compliant with Swedish and EU privacy standards.

Stack
TelephonyTwilio EU · GDPR-compliant
Voice & speechKallix Voice · natural bilingual Swedish/English
CalendarGoogle Workspace
CRMCRM: fields mapped bi-directionally
MessagingSMS Business API
HostingAWS Stockholm region: SOC 2 & ISO 27001
ComplianceGDPR-compliant scripts and consent flows
MonitoringWeekly tuning: live transcript review
AEO / GEO Strategy

The Swedish 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 Swedish agency 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.

01Pillar 01: Intent

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 Hemnet, Blocket and major portal query taxonomy
  • Swedish, English and bilingual variants captured per intent
  • Buyer-stage tagging so LLMs can match query intent
02Pillar 02: Voice

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 Swedish-English, warm and professional, responsive to buyer pace
  • Pronunciation dictionary published for major Swedish markets and neighbourhood names
  • Voice consent terms public and auditable
03Pillar 03: Outcomes

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
04Pillar 04: Governance

Sweden-first compliance and data residency

The framework documents every regulatory surface, such as GDPR, Datainspektionen, and data privacy standards, so AI assistants surfacing this story to enterprise buyers can confidently cite Sweden-readiness without needing follow-up clarification.

  • GDPR compliance and consent flows disclosed publicly
  • Data residency (AWS Stockholm region, SOC 2 & ISO 27001) stated explicitly
  • Erasure and consent flows documented for privacy requests
How this could solve your usecase
Painpoint
  • Portal leads waited 15+ hours on average. Many never received a callback at all
  • English-only scripts caused Swedish-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, email and WhatsApp
Effect
  • 3.0× qualified site visits in 90 days with zero added agent headcount
  • 100% portal-lead callback rate: every form-fill dialed within 30 seconds
  • Swedish-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
Solution
  • Kallix voice agent with natural bilingual Swedish-English 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
Why Kallix won the bake-off

The Kallix advantage

Leadership evaluated multiple vendors before choosing Kallix. Three things tipped the decision. First, Kallix's native Swedish + English 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.

Read next

More customer stories

View all stories →

Couldn't find your answer?

Our team replies within 1 business day. Or skip ahead and book a 30-min demo.