Production Case Study · Real Estate🔒 NDA Protected

AI Leasing and Maintenance Operations Platform

A regional property management company operating 1,400 units across 22 properties was losing £890,000 annually to preventable vacancy days and failed after-hours leasing conversions. Mirlo Systems deployed an AI leasing agent, automated maintenance routing pipeline, and live NOI dashboard, cutting vacancy turnaround from 22 to 11 days.

11 daysAverage Vacancy Turnaround
£890KAnnual NOI Improvement
34%After-Hours Conversion Rate
AI Leasing Agent and Property Operations Platform — Mirlo Systems
TL;DR

Executive Summary

A regional property management company operating 1,400 units across 22 properties was losing £890,000 annually to preventable vacancy days and failed after-hours leasing conversions. Mirlo Systems deployed an AI leasing agent, automated maintenance routing pipeline, and live NOI dashboard, cutting vacancy turnaround from 22 to 11 days. Built in 12 weeks with zero-downtime cutover and AES-256 encrypted pipelines.

01 · Business & Technical Challenge

The Challenge

Operational Friction

The company managed 22 properties with a leasing team of 12 and a field maintenance team of 8. Three compounding problems had been accepted as operational norms rather than solvable system failures. Average unit vacancy ran at 22 days against an achievable 11-day benchmark, with each excess day costing between £85 and £130 per unit. Across the portfolio, excess vacancy was eroding £890,000 in annual NOI. Leasing inquiries received after 6 PM or on weekends received no response until the following morning. Prospects who had contacted multiple properties had committed elsewhere by the time the leasing team called back, producing an after-hours conversion rate of 11% against 38% for same-hour responses. The leasing team absorbed maintenance triage work because no structured routing system existed. Coordinators spent 14 hours per week logging, routing, and chasing maintenance requests, time that should have been directed at prospect conversion and lease renewals.

Business Risks at Stake

  • Risk of losing 30 to 40% of prospects to competitors who respond to leasing inquiries within minutes rather than the next business morning
  • Risk of leasing coordinators continuing to absorb maintenance triage work as the portfolio scales, creating a structural staffing bottleneck
  • Risk of ownership making capital allocation decisions on portfolio data that is 5 to 7 days behind operational reality
02 · Solution Architecture & Technical Execution

The Solution

Mirlo Systems completed a 3-week discovery phase mapping the full workflow from inquiry to signed lease and from maintenance request to portfolio report. The platform was built in 12 weeks across three integrated systems, staged in an isolated environment, and deployed with zero-downtime cutover. The AI Leasing Agent was a voice and web chat system grounded on live AppFolio data, handling inbound inquiries around the clock, qualifying prospects, and booking viewings directly into the leasing calendar. Within 30 days, 62% of after-hours inquiries that previously received no response were being handled automatically. The Maintenance Triage Pipeline replaced the manual process where coordinators logged and routed field maintenance requests. Requests via voice, web form, and SMS were classified and assigned to the correct vendor or technician automatically, returning 14 hours per week of coordinator capacity to proactive lease renewal outreach.

Technology Stack

AppFolio PMSAnthropic ClaudeTwilion8n Workflow AutomationSupabase

Engineering Capabilities Delivered

  • 24/7 AI leasing agent handling voice, SMS, and web inquiries with live AppFolio inventory sync
  • Automated maintenance request classification across trade categories with GPS-proximity technician dispatch
  • After-hours inquiry pipeline converting 34% of prospects who previously received zero response
  • Automated tenant status updates at maintenance submission, dispatch, arrival, and job completion milestones
  • Live portfolio NOI dashboard with anomaly alerts on occupancy, delinquency, and maintenance cost deviation

Execution Approach

Proof-of-Concept FirstAgile / Sprint-Based BuildSecurity & Compliance HardeningZero-Downtime CutoverDedicated Onboarding & Handoff
03 · Business Value & Tangible Results

Measurable Outcomes

Verified Performance Results

  • Average vacancy turnaround: Reduced from 22 days to 11 daysPost-deployment 90-day operational review, AppFolio vacancy data
  • Annual NOI improvement: £890,000 recovered from vacancy reduction aloneAnnual financial comparison, ownership reporting
  • After-hours inquiry conversion rate: Increased from 11% to 34%Leasing pipeline CRM data, 60-day post-launch period
  • Leasing coordinator capacity recovered: 14 hours per week per coordinator returned to leasing activityTime-tracking audit, 30 days before vs. 30 days after
  • Portfolio reporting cycle: Eliminated 5-7 day lag - live real-time dashboard from day oneOperations team workflow audit

Before vs. After

Average vacancy turnaround
Before22 days
After11 days
50% reduction
After-hours inquiry conversion
Before11%
After34%
+209% improvement
Portfolio reporting lag
Before5-7 days behind real-time
AfterLive dashboard
Eliminated entirely
Leasing coordinator maintenance hours
Before14 hours per week
AfterZero
Full elimination
Annual NOI from vacancy
Before£890K shortfall
After£0 shortfall
£890K recovered

Qualitative Gains

  • Zero manual administrative friction in routine processing pipelines.
  • Enhanced staff operational capacity redirected to high-value client interactions.
  • Full compliance and security audit trail maintained across all automated pipelines.

Find your starting point

Wherever you are with AI, we meet you there

Select your current stage of AI adoption to see how Mirlo Systems helps you move forward with clarity and measurable ROI.

  • Stage 01

    "We haven't started with AI yet"

    Not sure where AI actually fits in your operation. We run a focused audit, show you exactly where it pays off, and build a prioritized roadmap - before you spend on anything.

    AI Strategy & AdvisoryAuditRoadmap
  • Stage 02

    "We tried AI and it didn't stick"

    A chatbot or off-the-shelf tool didn't hold up in real operations. We rebuild it properly - integrated with your actual systems and tested against real workload, not a controlled test.

    Custom AI DevelopmentIntegrationRebuild
  • Stage 03

    "AI is working, we want more of it"

    One system is proving out. Now scale it - more coverage, more automation, better reporting - without breaking what's already working.

    Workflow AutomationAI Reporting & AnalyticsScale

Proof & Validation

Common Questions

The leasing agent operates with a defined scope covering availability, pricing, viewing booking, pet/parking policies, deposit requirements, and tenancy terms. Any query outside scope is escalated to a named leasing coordinator with full transcript.

How does the AI leasing agent handle inquiries it cannot answer accurately?
The leasing agent operates with a defined scope covering availability, pricing, viewing booking, pet/parking policies, deposit requirements, and tenancy terms. Any query outside scope is escalated to a named leasing coordinator with full transcript.
How was the integration with AppFolio handled without disrupting live operations?
The integration was developed and tested in an isolated sandbox environment throughout the build phase and validated via a 2-week parallel running period before live cutover.
What happens to tenant data within the AI leasing and maintenance systems?
All tenant data is processed within an isolated production environment with AES-256 encryption at rest and in transit under a zero-data-retention policy with LLM providers.
Can the portfolio intelligence dashboard be extended to additional data sources?
Yes. The dashboard is built on a source-agnostic central data layer that connects PMS, accounting, and maintenance routing pipelines.
What does the ongoing support arrangement include after go-live?
Post-launch support includes a named engineering contact, SLA-backed response times, monthly performance reviews, and staging environment access.