Real Estate · Conversational AI

Conversational AI enquiries: warm leads before agents pick up the phone.

WhatsApp, web chat, and voice handled in real time — qualified in the buyer's language, with the viewing slot booked before the thread closes. Human agents step in on a warm thread, not a cold one.

intake-console · conversationLIVE
SESSION · SESS-22481
WhatsApp Business
LANGUAGE
Bahasa Melayu · auto
14:02 SGT
CONVERSATION
Hi, saya minat rumah di Damansara Heights.
Selamat petang! Boleh saya tahu bajet dan bila nak move in?
Bajet MYR 1.8M, move dalam 3 bulan.
Baik. Sabtu 2pm boleh tengok show unit?
INTENT
Owner-occupier
ROUTING
Faizal T. · KL
CONVERSING…
Faizal T.
Sat 2pm · show unit

What we build

Every channel, every language, every hour.

Each capability runs in production against your live enquiry stream — wired to your CRM, calendar, and inventory on day one.

Multi-channel intake

Web widget, WhatsApp Business API, and phone IVR unified into one inbox — every enquiry scored and routed through the same pipeline regardless of entry point.

In-conversation intent detection

Is this a qualified enquiry or someone asking for a brochure PDF? The intent classifier reads the thread continuously and only escalates when there's real sales signal.

Live language detection + reply

EN, BM, ZH, TH, ID, VI auto-detected mid-conversation. Language switches are honoured turn-by-turn — buyers never feel forced back into English to make progress.

Appointment booking inside the chat

Calendar-aware slot pitching against agent availability and project gallery hours — the appointment is booked before the thread closes, not after a callback.

Brand-voice tone matching

Trained on your developer voice — same cadence, same positioning, same approved phrases. Replies sound like your brand, not a generic chatbot.

After-hours coverage + escalation

The agent qualifies and books out-of-hours; warm leads are handed off to a named human agent the next morning with the conversation history attached.

Who runs this

Every channel, same intake engine.

Whether the enquiry lands in a web widget on launch weekend or a voice call on a Sunday afternoon — the intent classifier, slot extractor, and brand-voice generator are the same. Only the channel adapter changes.

01

New-launch EOI funnels

Launch-weekend enquiry floods handled without human bottlenecks. Every conversation qualified and gallery-slot-booked before a single agent manually replies.

02

Resale + lettings intake

Multiple listings, same intake engine — the AI knows which listing each enquiry is about, references photos, and books viewings in the chat.

03

Multi-country property portals

SG, MY, ID, TH, VN coverage with per-market language, phone number formatting, and business-hours logic baked into the same platform.

04

WhatsApp-first developer sales

Where WhatsApp is the dominant channel (SEA-wide), the AI picks up inside the BSP thread, handles media responses, and escalates to agents on pattern triggers.

05

Agency co-broke intake

Agency-rep enquiries recognised and separated from direct buyers — routed to the co-broke desk with commission splits and protocol rules attached.

06

Voice IVR replacement

AI voice handles phone enquiries end-to-end — qualifies, books gallery visits, and drops transcripts into the CRM with the audio recording attached.

A walk-through

From first message to booked viewing — in five steps.

Walk through a live agency deployment — how enquiries are greeted, clarified, qualified, booked, and handed off to a named agent.

DEPLOYMENT · ATLAS-SEA-01
Atlas Realty Group Pte Ltd· 1,200 agents · SG / MY / ID / TH · multi-channel conversational intake
STEP 01 · 05
STEP 01 · GREET
Answered the moment it lands
WhatsApp, web-chat, or voice — the enquiry gets an on-brand reply inside ten seconds, even at 11pm or during launch weekend surges.
Multi-channel intake live
Agents on call 24/7 — without staff on call 24/7
WhatsApp Business
BSP webhook · SG / MY / ID
3.2s
Web chat widget
Developer sites · WCAG 2.2
1.8s
Voice IVR
Inbound AI agent · SEA
2.1s
AVG GREET LATENCY
2.4s
AFTER-HOURS COVERAGE
100%
ON-BRAND TONE MATCH
98.7%
LANGUAGES LIVE
6

Model families we deploy

Four specialised models. One seamless conversation.

Each model owns a layer — intent, slots, voice, escalation. Composing them per turn gives you reliability a single end-to-end model can't match.

MULTILINGUAL · 12 SEA LANGUAGES
Intent Classifier
0.93 F1 · intent

Multilingual transformer classifying enquiry intent (information · qualification · objection · booking). Runs per-turn so pivots are caught inside the thread, not after it.

BUDGET · TIMELINE · UNIT-TYPE · AREA
Slot-Filling Extractor
< 80ms · p95

Structured extraction model pulling slot values from every message — each slot versioned per turn so an agent joining late sees the latest qualified view at a glance.

DEVELOPER-VOICE FINE-TUNE
Brand-Voice Generator
< 900ms · p95

Reply generation trained on your approved scripts, brand book, and top-performing human conversations. Outputs cleared by guardrails before send.

RL-STYLE THRESHOLD LEARNING
Escalation-Trigger Policy
+22% warm handoff

Learns when to hand off — from objection signals, high-intent triggers, or after-hours qualification completion. Escalation rules retrain against agent feedback weekly.

Data sources wired into every conversation

Every channel, integrated — every reply, grounded.

Channel adapters, calendar sync, and inventory lookup all live in the same conversation loop — no hallucinated availability, no stale unit status.

Source
Format
Cadence
Purpose
Web chat widget
JS SDK · event stream
Live
Primary first-party channel — captures UTM, page path, and scroll signals alongside the conversation for intent inference.
WhatsApp Business API
BSP webhook · media-capable
Live
Dominant SEA channel — text, image, and voice-note handling with BSP-compliant session management and template messaging.
Phone IVR + ASR
SIP trunk · Whisper-tier ASR
Live
AI voice handles phone enquiries — full-duplex audio with barge-in, language auto-switching, and transcript + audio persisted per call.
Calendar / appointment system
Google Calendar · Calendly · Outlook
Bi-directional
Slot availability queried and booked inside the chat — appointments writeback to the agent's calendar with conflict detection.
Agent availability feed
Rota + CRM activity
Real-time
Handoff respects agent workload, language, and territory — never dumps a warm lead on an agent who's mid-viewing.
Project / inventory source of truth
CRM · MLS · developer system
Scheduled sync
The AI only pitches units that are actually available — unit status (available · reserved · sold) honoured per-conversation.

Reasoning, not replies

A reply alone isn't enough. The chain of intent, slots, and handoff reasoning is.

Every conversation logs the intent classifications, slot extractions, and escalation decisions that produced the agent experience. Managers audit threads at scale, not one-by-one.

  • Per-turn intent + slot state with confidence
  • Source-of-evidence quote for every extracted field
  • Escalation rationale with policy version attached
  • Full transcript + audio with retention per jurisdiction
CONVERSATION AUDIT · LEAD-C8241
convo.explain v2.1
ChannelWhatsApp · BM
Intent · t+7qualification · 0.89
Budget extractMYR 1.8M · msg 4
Timeline extract3mo · msg 6
Slot bookedSat 14:00 · Faizal T.
Policy versionescalation v1.8
Audit SHAa7d2…4b19

Compliance & governance

Consent, disclosure, and residency — by design.

Per-jurisdiction consent, disclosure, and retention — enforced in the conversation layer, not bolted on as a banner.

Every control below ships with the deployment.

Consent capture on channel entry

Every channel — web, WhatsApp, voice — captures consent on first contact, with platform-specific wording. Consent version travels with every message.

AI-agent disclosure per message

Per-jurisdiction disclosure rules honoured (mandatory disclosure in CA; soft disclosure elsewhere) with a human handoff option always one message away.

PDPA SG + PDPA MY alignment

Per-jurisdiction residency tagging enforced. Messages and audio recordings never cross borders for processing without explicit cross-border consent.

After-hours handoff audit

Every out-of-hours qualification logs the qualification trail so the morning-shift agent sees why the AI escalated and what was promised to the buyer.

Recording-retention policy

Voice recordings retained per jurisdiction rules with automatic purge schedules — regulator-ready export available per contact on demand.

Quiet-hours regional rules

Marketing-message quiet hours honoured per-market (e.g. Malaysia 9pm–9am rules) with session-based exceptions for active qualifications buyers initiated.

Frameworks we align to

PDPA SGPDPA MYPIPLCCPAISO 27001SOC 2W3C WCAG 2.2WhatsApp Business Policy

Why Axccelerate for conversational intake

Not a chatbot.
An intake system.

Off-the-shelf chatbots answer FAQs. Our stack qualifies, books, and hands off — with reasoning trails and retraining against your sales outcomes.

Feature
Axccelerate
Generic chatbot
In-house
Multi-channel intake (web + WhatsApp + voice)
Varies
Varies
Live language detection (EN/BM/ZH/TH/ID/VI)
In-chat slot booking w/ calendar awareness
Varies
Brand-voice fine-tune (developer-specific)
Varies
Intent + slot extraction per turn
Varies
AI voice IVR (full-duplex, barge-in)
Escalation-policy retraining on feedback
Varies
PDPA + PIPL residency enforcement
Varies
Quiet-hours + after-hours governance
Varies
Varies
No vendor lock-in

Pricing

Priced to your channel mix, not per-message.

Every deployment is scoped against your channels, languages, and enquiry volume before we quote — no per-message trap pricing.

Launch
Enquirefor pricing
Single channel

One channel — web chat or WhatsApp — with intent detection, slot booking, and brand-voice reply, wired to your CRM and single project inventory.

1 channel (web or WhatsApp)
2 languages (EN + 1 local)
Calendar + CRM integration
Intent + slot extraction
Weekly policy retraining
Enquire for pricing
Most popular
Scale
Enquirefor pricing
Multi-channel portfolio

Web chat · WhatsApp · voice IVR across a developer portfolio, with project-aware responses, per-project inventory awareness, and multi-agent handoff logic.

All channels (web + WhatsApp + voice)
Up to 4 languages
Per-project inventory + voice
Supervisor console + transcripts
Bi-weekly model reviews
Enquire for pricing
Fleet
Enquirefor pricing
Multi-language enterprise

12-language coverage across SG/MY/ID/TH/VN/PH with dedicated voice/chat engineering, jurisdiction-specific governance, and enterprise SLAs.

Unlimited channels · 12 languages
Per-jurisdiction residency stacks
Dedicated engineering team
24/7 monitoring + on-call
Enterprise SLA + DPA
Talk to us

FAQ

Common questions.

Don't see your question here?

Ask us directly

Glossary

The vocabulary behind every conversation.

A reference for the terms your sales team, compliance team, and conversation platform will all share.

BSP
WhatsApp Business Solution Provider

Meta-approved infrastructure provider for WhatsApp Business API (e.g. 360dialog, Wati, Infobip). All enterprise WhatsApp goes through a BSP — direct-to-Meta isn't an option for most use-cases.

IVR
Interactive Voice Response

The phone-menu system that used to say 'press 1 for sales'. AI IVR replaces it with natural conversation — buyers describe what they want, the AI qualifies and books without buttons.

ASR
Automatic Speech Recognition

Speech-to-text. Modern ASR (Whisper-tier) handles SEA accents, code-switching, and noisy environments — the accuracy jump since 2022 is what made AI voice viable for property intake.

NLU
Natural Language Understanding

The layer above raw text — extracting intent, entities, and slots from what a buyer says. Separate from generation (NLG). Our stack uses NLU per turn to decide handoff timing.

Intent
Classification of user goal

Per-turn label like 'information-request', 'qualification-in-progress', 'objection', 'booking-intent'. Intent drives policy — only qualification-complete or booking-intent triggers escalation.

Slot
Structured extracted value

Discrete qualified fields — budget, timeline, unit-type, area preference. Slots get filled progressively across the conversation and are the handoff payload to human agents.

Fallback
When the AI can't answer confidently

A routing decision — to a human, to a clarifying question, or to a disambiguation prompt. Fallback rates are one of the health metrics we monitor per-project weekly.

Handoff
AI → human transition

The moment responsibility moves from AI to a human agent. Our handoffs carry transcript, slots, intent, and any promises made — the human agent never walks into a cold thread.

Escalation
Priority handoff trigger

Specific patterns that bypass normal queues — explicit buyer frustration, objection patterns, booking-intent with no slot conflict, etc. Escalation rules retrain against agent outcomes.

Session
WhatsApp 24h interactive window

After any user message, there's a 24h window for free-form agent replies. Outside it, only pre-approved templates can send. Session management is a core operational discipline in WhatsApp.

Latency p50/p95
Response-time percentiles

Median (p50) and 95th-percentile (p95) response times. We target p50 < 400ms and p95 < 900ms for chat replies — fast enough to feel like a real conversation, not polling.

Turn-taking
Who speaks next

In voice, the model must decide when the buyer has stopped speaking and it's the AI's turn. Getting this wrong is the #1 reason AI voice feels robotic.

Barge-in
Interrupting the AI mid-sentence

When a buyer starts speaking while the AI is still talking, the AI should stop and listen. Humans do this constantly — voice AI that can't barge-in feels like an IVR of the 2010s.

Language auto-detection
Per-turn language inference

The classifier that decides which language this particular message is in — critical in SEA where buyers code-switch mid-sentence (e.g. English with Bahasa words interspersed).

Multi-channel · multi-language · 24/7

Every enquiry warmed. Every viewing booked.

30-minute scoping with a senior engineer and a conversation-ops operator. You'll leave with a channel plan, language matrix, and deployment timeline — not a sales pitch.