Case Study — 02

Property
Guide
Agent

An AI voice agent deployed at a live open house. Real environment, real guests, real results.

99% accuracy across 60+ live interactions in a genuinely noisy open house environment.
Role Founder & PM
Company Iro AI
Timeline 7 Days to Live
Launch 14 Nov 2025
Product AI Voice Agent
99%
Conversation accuracy — validated in a live, noisy open house
60+
Live attendees interacted with the AI at the launch event
7
Days from concept to live deployment — including testing
1
Unsolicited referral + LinkedIn recommendation within days of launch

Core Insight: Property viewings are completely dependent on agent availability. When an agent is unavailable, buyers wait — or they leave. This system made the property open for self-guided tours without requiring a full-time agent on site, turning every unlock into a guided, qualified interaction.

The Problem

Real estate agents are spread thin. A single agent might be responsible for multiple listings simultaneously — phone calls, client meetings, paperwork, and physical showings all competing for the same hours.

The result? Buyers arrive at a property and wait. Or they don't arrive at all because scheduling is too much friction. Every missed showing is a potential deal lost — not because the property is wrong, but because the system failed to support the buyer at the moment of highest intent.

The Old Way

Human-dependent showing

Agent must be present. Scheduling friction. No support if agent is unavailable or running late. Buyer experience is inconsistent and entirely agent-dependent.

The AI Way

Event-triggered automation

Lock triggers AI. AI calls buyer within 60 seconds. Greets by name, guides room-by-room, answers questions in real time. Consistent, warm, available 24/7.

The Product Experience

The experience was designed to feel warm and personal from first contact — not robotic, not transactional. The goal was never just information delivery. It was making people feel genuinely cared for and respected at every step of the property journey.

Buyer Journey

Buyer receives a temporary smart lock access code
Unlocks the front door — webhook fires instantly
AI calls within 60 seconds — greets buyer by name
Guides room by room — features, questions, warm conversation
Handles 6–8 questions per tour in real time
Keeps interaction warm — small talk included

For the open house event, a QR code trigger was added so guests could initiate a call manually — adapting the system to a crowded, social environment while keeping the same quality of conversational experience.

System Architecture

The system is built on a simple, event-driven principle: the door unlock is the trigger. Everything flows from that single event — no manual input, no scheduling, no human in the loop required.

🔐
Door Unlock
Smart lock event
Webhook
Buyer details fired instantly
🤖
AI Initiates Call
Within 60 seconds
🏠
Guided Tour
Room-by-room, live Q&A

Two conversational personas were built, each trained on the full property knowledge base. The routing decision was handled automatically, with both agents designed to feel distinctly human — different cadences, different warmth profiles, both optimised for the specific property context.

ComponentDetail
Trigger mechanismSmart lock webhook → real-time event dispatch
Call initiation window< 60 seconds from door unlock
Conversational personas2 — distinct voices & cadences, same knowledge base
Knowledge baseFull property data: specs, features, neighbourhood, pricing
Open house triggerQR code (manual call initiation for event context)
Avg. interaction duration~4 minutes
Questions handled per tour6–8 real-time
Property Guide Agent — product flow diagram showing door unlock to AI call to guided tour
↑ Product flow — from smart lock trigger to guided AI property tour

Hear It Live

These are real recordings from the live open house event on 14 Nov 2025. Two conversational AI personas — different voices, same property knowledge, same standard of warmth. These were recorded in the live environment, with background noise, real guests, real questions.

🎙️
Ava — Conversational Persona 1
Recorded live · Open House · 14 Nov 2025
Live recording — ambient noise intentional. This is how it sounded in the room.
🎙️
Milo — Conversational Persona 2
Recorded live · Open House · 14 Nov 2025
Live recording — different persona, same property knowledge base and 99% accuracy standard.

Build Snapshot

Seven days. Concept to live deployment. This wasn't a prototype — it was a production system running at a real event with 60+ attendees and zero handholding once live.

⚡ Concept → Live in 7 days · Including testing
MetricValue
Total build time7 days (including testing)
Conversational personas2
Real-world accuracy99%
Average interaction time~4 minutes
Typical questions per tour6–8
Launch event14 Nov 2025
Live attendees at launch60+

Launch — Open House

The system went live at a real open house — not a controlled demo, not a staging environment. The room was loud. Conversations overlapped. People were moving around. These are exactly the conditions that expose weaknesses in voice AI.

The agents held up. 99% accuracy across every interaction. Guests didn't just use the product — they enjoyed it. The experience felt novel and personal, not robotic.

The Environment

Conditions that expose AI weakness

60+ guests simultaneously. Background noise. Overlapping conversations. People moving between rooms mid-sentence. Real-world chaos — not a lab.

The Result

What actually happened

99% accuracy. Zero system failures. Guests engaged, asked questions, stayed on the call. The AI felt warm and capable — not a gimmick.

Client Outcome

Organic Referral. Zero Outbound.

The client referred Iro AI to another founder in his network — without being asked. An unsolicited LinkedIn recommendation followed within days of the launch going live.

Client Response · Post-Launch
"The client referred Iro AI to another founder in his network — without being asked."

Unsolicited referral within days of going live · Followed by a LinkedIn recommendation

Validation Signal
"An unsolicited LinkedIn recommendation followed within days of the launch."

This is the clearest validation: a client so satisfied they became an advocate before the engagement was even fully wrapped.

This is the clearest validation signal available pre-revenue: a client so satisfied by the work that they actively advocate for the product to their professional network, unprompted, within the first week of going live.

What This Demonstrates

This project sits at the intersection of conversational AI design, event-driven system architecture, and rapid product delivery. Each skill is validated not in theory but in a genuinely challenging live environment.

💬

Conversational UX Design

Building AI agents people actually want to talk to — warm, natural, not robotic.

Event-Triggered Automation

Webhook-based real-time orchestration from physical trigger to AI response in <60s.

🎙️

Voice AI Orchestration

Multi-persona routing with full property knowledge base integration.

🚀

Rapid Product Deployment

Concept to live production system in 7 days, including testing.

🛡️

Real-World Resilience

99% accuracy in a noisy live environment — not a controlled lab setting.

📐

System Architecture

End-to-end event-driven architecture from smart lock to AI conversation.

Key Learnings

01

Warmth is a product feature, not a nice-to-have

Guests didn't just tolerate the AI — they enjoyed it. The conversational design specifically focused on making people feel cared for, not processed. That's a deliberate product choice, not a side effect.

02

Live events are the ultimate stress test

No controlled demo environment catches what a real open house with 60+ people will expose. Deploying into chaos proved the system's resilience more convincingly than any internal QA process could.

03

Speed of deployment unlocks real signal

7 days. The value of moving fast isn't just efficiency — it's that you get real feedback, real results, and real referrals before slower-moving competitors have finished their planning cycle.

04

Unsolicited referrals are the real product-market fit signal

NPS, surveys, and reviews are proxies. A client who actively refers you to their network — before you've even asked — is the real thing. That's the signal this product generated within days.