Bayleys Property Valuation app upgrade with AI

About the Client

Bayleys Real Estate is New Zealand’s largest full-service real estate agency, operating across residential, commercial, rural, and property management services across New Zealand and Australia. With over 150 property management agents generating 1,800 to 2,000 rental appraisals per month, the manual documentation workload was significant, inconsistent across regions, and a major drain on agent productivity.

The leadership team — including the National Director and Financial Director — identified AI-driven automation as the strategic priority, with a clear mandate: cut appraisal time, improve consistency and accuracy, and free agents to focus on client relationships rather than documentation.

Project Background

Bayleys was already running a modern AWS-hosted property search web application built by Peritos Solutions — giving agents a cloud-based way to search and manage property records from any device. The next phase was to add AI intelligence on top of that foundation.

Each rental appraisal required an agent to manually research comparable properties, write a property description, calculate a market rent range, pull together agent branding and contact details, and format everything into a professional PDF. This 30 to 45 minute process, repeated thousands of times per month, was the single biggest time drain in the property management workflow.

Peritos Solutions was engaged to design and build the AI upgrade: automating the appraisal document, training a mathematical valuation model on historical data, deploying an AI copywriting engine for property descriptions, and building the AskKen AI chatbot for on-demand knowledge access.

Requirements

Generate a complete, professional, branded rental appraisal report in under one minute — from a single property address entry
AI-generated property description — trained on thousands of historical Bayleys appraisals to match the tone and style of an experienced property manager
EMV (Estimated Market Rent) calculated by a machine learning model trained on historical sales and rental data — accuracy within ±3% of experienced agent assessment
Property attributes (bedrooms, bathrooms, floor area, carparks) automatically retrieved via CoreLogic API
Property listing image automatically pulled via Bayleys API where the property is currently listed for sale
Agent profile photo, name, contact details, and office auto-populated via Office 365 Single Sign-On
School zones and local amenities automatically identified from property address
Support for multiple property types — house, apartment, unit, minor dwelling, home and income
Manual entry flow for new-build and off-plan properties not yet in CoreLogic or Bayleys systems
90-day appraisal expiry logic — stale reports cannot be shared without manager review
Regional disclaimer management configurable by administrators
AskKen AI chatbot — zero-training, conversational interface covering legislation, tribunal cases, market data, maintenance costs, yield calculations, and suburb intelligence
RAG architecture grounding all AI responses in controlled Bayleys proprietary data — not the open internet

Scope & Feature List

Module 1 — Automated Rental Appraisal Report

A property manager enters or confirms the property address. The system generates a complete, professionally formatted, Bayleys-branded rental appraisal report automatically:

Property address triggers automatic data retrieval from CoreLogic API — bedrooms, bathrooms, floor area, carparks, property type
Property image pulled from Bayleys listing API if the property is currently listed for sale — ensuring brand-consistent presentation
Agent profile, photo, and contact details auto-populated via Office 365 SSO — the system knows who is logged in
EMV rental range calculated and displayed — powered by the Random Forest valuation model (see Module 2)
AI-generated property description inserted automatically — see Module 3
Rental details section populated: current market value range, property type, report date
Regional legal disclaimer appended — configurable per region, with 90-day expiry logic built in
Back-page advert customisable by region or individual agent — uploaded via application settings
Multiple property types supported — houses, apartments, units, minor dwellings, home and income
Manual entry available for new-build and off-plan properties — feeds directly into the Bayleys Data Lake
Output: professional PDF matching Bayleys national branding guidelines — consistent across all 150+ agents and all regions

Module 2 — EMV (Estimated Market Rent) Valuation Engine

The EMV engine is the mathematical centrepiece of the platform. Peritos evaluated multiple modelling approaches and selected a Random Forest Regression model, trained on data from the Bayleys Data Lake, as the optimal fit for rental valuation.

The model was refined through three stages to achieve ±3% accuracy against experienced agent assessments:

Initial model (basic property features only) — margin of error exceeded ±15%, predictions unreliable at extremes
After geometric mean aggregation of decision tree outputs — outlier influence dampened, error narrowed to ±8–10%
Final model with full feature set, Pearson R local correlation between capital value and existing rental price weighting, and property subjective rating (manual label by agents in the training data) — ±3% accuracy nationwide

Key technical components:

Bootstrap aggregation (bagging) — many de-correlated decision trees built from different samples of the Data Lake, predictions averaged to reduce variance
Geometric mean aggregation — dampens the influence of extreme outliers across individual tree predictions, particularly effective in large heterogeneous suburbs such as Remuera
Suburb and street-level Pearson R correlation analysis — calculates the relationship between property Capital Value (CV) and actual rent for every suburb in New Zealand, dynamically weighting CV’s influence in the regression per location (e.g. R=0.93 in Epsom = CV carries very high weight; lower R suburbs rely more on physical features)
Resolves the classic valuation dilemma of ‘best house on the worst street vs. worst house on the best street’ by varying feature weights by suburb rather than applying a national average
New property data entered manually by agents (for off-plan/new builds) feeds back into the Data Lake — improving model accuracy over time, especially in newly developed suburbs

Module 3 — AI-Generated Property Descriptions

Property descriptions are generated automatically by an AI model trained specifically on Bayleys‘ historical appraisal data. Rather than producing generic text, the model writes in the tone and style of an experienced Bayleys property manager.

Trained on thousands of historical rental appraisals from across New Zealand — using sentiment analysis to learn how Bayleys property managers write
The AI engine analyses the property address to identify local amenities, school zones, and suburb characteristics — incorporating these naturally into the description
Property type, bedroom count, bathroom count, floor area, and key features are woven into the description based on data retrieved from CoreLogic
Output is inserted directly into the appraisal report — agents can review and edit if needed, but in most cases the AI description is used as-is
New property data entered manually also contributes to future description training — the system improves with every appraisal generated

Example output: ‘Large 5-bedroom, 3-bathroom home with triple car garaging, heated swimming pool and spa pool… Located close to Kohimarama Beach and top schools — Kohimarama School and Selwyn College. Whole house (5 beds): $1,650–$1,800pw’

Module 4 — AskKen AI Legal & Market Chatbot

AskKen AI is a purpose-built real estate intelligence assistant, powered by OpenAI GPT-4O with a custom AI engine layered on top to control output quality and data sourcing. It is accessible via mobile and desktop and requires zero training to use.

Architecture — Retrieval-Augmented Generation (RAG):

Proprietary documents — the Residential Tenancies Act, related legislation, tenancy tribunal cases, suburb profiles, maintenance cost databases, and vendor checklists — are ingested, indexed in a vector store, and retrieved at query time
54,000 tenancy tribunal cases ingested — giving the model deep contextual and interpretive legal capability, not just raw legislative text
GPT-4O responses are grounded in Bayleys‘ controlled data sources — not the open internet; external web search is disabled by default
Filtering and guardrails layer reviews all outputs against compliance checklists, strips unsupported assertions, and flags uncertain answers for human review
Knowledge management layer tracks document version and effective date — new legislation or tribunal decisions can be re-indexed automatically

AskKen AI handles queries across:

Residential Tenancies Act legislation and compliance obligations
Tenancy tribunal precedents and case outcomes — with specific case references
Comparable property market analysis and recent rental data
Suburb profiles, school zones, and local amenity information
Rental market reports and suburb-level rent trend analysis
Maintenance cost estimates, depreciation calculations, and IRD schedules
Yield calculations — factoring in rent, management fees, rates, insurance, vacancy, and mortgage interest
Checklists — fixed-term tenancy breaks, property inspections, new tenant onboarding

Solution Architecture

Technology & Architecture

The AI platform is built cloud-native on AWS, with OpenAI -GPT-4O powering the language generation layer. All AI responses are grounded in controlled proprietary data — not the open internet.

Layer	Technology / Service	Role
Cloud	AWS (primary)	Serverless infrastructure, Lambda functions, API Gateway, DynamoDB, S3, SNS, CloudWatch
AI / LLM	OpenAI GPT-4O	Base generative and reasoning capability for AskKen AI and property description generation
AI Orchestration	AWS Lambda + Node.js/Python	Microservice orchestrating: user input → RAG retrieval → LLM call → answer filtering → UI response
EMV Model	Random Forest Regression	Trained on Bayleys Data Lake — bootstrap aggregation, geometric mean, Pearson R suburb weighting — ±3% accuracy
RAG Layer	Vector store + proprietary docs	54,000 tribunal cases + legislation + market data indexed — retrieved at query time to ground LLM responses
Data Layer	Bayleys Data Lake	Historical appraisals, rental data, property records, new-build manual entries — feeds EMV model training
Property Data	CoreLogic API	Bedrooms, bathrooms, floor area, carparks — retrieved automatically on address entry
Images	Bayleys Listings API	Current listing photos pulled into appraisal report automatically for listed properties
Auth	Office 365 SSO	Single sign-on — agent profile, photo, and contact details auto-populated in every report
Security	AWS WAF + token auth	Web Application Firewall + token-based API endpoints — all property and AI data secured
Guardrails	Rules engine	LLM outputs reviewed against compliance checklists; unsupported assertions stripped before reaching the user

Application Images

Implementation Approach

The project kicked off in October 2024 and delivered an MVP into UAT for Auckland agents by early March 2025 — on schedule and within budget:

Phase 1 — Discovery	Requirements workshops, CoreLogic and Bayleys API integration scoping, data lake assessment, RAG document inventory, architecture design on AWS
Phase 2 — EMV Model	Initial Random Forest baseline, geometric mean refinement, Pearson R suburb-level correlation weighting — iterated until ±3% accuracy achieved nationally
Phase 3 — Appraisal Engine	Automated report generation, CoreLogic integration, Bayleys API image pull, Office 365 SSO, multiple property type handling, 90-day expiry logic
Phase 4 — AI Descriptions	GPT-4O fine-tuning on historical Bayleys appraisals, sentiment analysis training, school zone and amenity integration, review and editing workflow
Phase 5 — AskKen AI	RAG pipeline build, document ingestion (legislation + 54,000 tribunal cases), guardrails layer, GPT-4O prompt engineering, chat interface on mobile and desktop
Phase 6 — UAT & Go-Live	UAT with Auckland property managers, regional disclaimer configuration, performance tuning, cost optimisation on AWS, go-live and hypercare

Challenges & Solutions

EMV accuracy from ±15% to ±3%	Initial models had very high variance. Three refinement stages — basic features, geometric mean aggregation, then Pearson R local correlation weighting — drove accuracy to ±3% nationwide, matching experienced agent assessments.
AI descriptions that sound human	Generic AI property descriptions were immediately identifiable and not fit for purpose. Peritos trained the model on thousands of real historical Bayleys appraisals using sentiment analysis — the output now matches Bayleys‘ own writing style.
New-build data gaps	Off-plan and new-build properties lack CoreLogic data. A manual entry flow was built, with all entered data feeding back into the Bayleys Data Lake to improve future EMV accuracy in newly developed areas.
RAG grounding vs. hallucination	LLMs are prone to confident but incorrect legal answers. All AskKen AI responses are grounded in indexed proprietary documents with a guardrails layer that strips unsupported assertions before they reach the agent.
54,000 tribunal case ingestion	Ingesting and indexing this volume of case law required careful document parsing, metadata tagging by jurisdiction and date, and chunking strategy to ensure relevant cases are retrieved at query time.
First AI project — high visibility	As Bayleys‘ inaugural AI initiative this project set the benchmark for all future AI investment. Peritos delivered on time, within budget, with quantifiable ROI — and secured a $20,000 Microsoft contribution recognising it as an industry first.
Stale appraisal compliance	Without controls, agents could share outdated market assessments. Built-in 90-day expiry logic prevents any appraisal older than 90 days being shared without a property manager review — protecting professional and legal standards.

Financial Impact

Appraisal time reduction	From 30–45 minutes per appraisal to under 1 minute — saving approximately 40 minutes per appraisal
Monthly appraisal volume	1,800–2,000 appraisals per month (60,000–67,000 annually)
Saving per appraisal	NZD $33.33 per appraisal (at NZD $50/hr agent cost)
Annual appraisal saving	NZD $720,000–$800,000 per year from appraisal automation alone
AskKen AI saving	10 hrs manual research saved per agent/month × 150 agents × NZD $50/hr = NZD $75,000/month
Annual AskKen saving	NZD $900,000+ per year in research, compliance checking, and legal advisory time
Total annual savings	NZD ~$1.75 million per year — combined appraisal automation + AskKen AI

Key Benefits

Appraisal turnaround time reduced from 30–45 minutes to under 1 minute — freeing agents to focus on client relationships
AI-generated property descriptions match the tone and style of experienced Bayleys property managers — consistent quality across all agents and regions
EMV accuracy of ±3% nationwide — matching or exceeding the estimates of experienced agents
AskKen AI gives every property manager instant access to legislation, tribunal cases, market data, and maintenance knowledge — without leaving the platform
Agent profile, contact details, and property images auto-populated via SSO and API integrations — zero manual formatting
New-build and off-plan data captured manually feeds back into the Bayleys Data Lake — building proprietary market intelligence ahead of public availability
90-day appraisal expiry and regional disclaimer management built in — compliance safeguards without any agent overhead
Stress and cognitive load reduced for property managers — repetitive tasks automated, accuracy protected
Platform scales across New Zealand and Australia from a single codebase on AWS
Recognised by Microsoft with a $20,000 contribution as an industry-first AI innovation

Support & Next Steps

Peritos Solutions provided post-go-live hypercare covering AI output quality monitoring, EMV model tuning, and integration stability. Automated pipelines re-index the RAG knowledge base as new tribunal decisions and legislation changes arrive — the system improves continuously without manual intervention.

Planned next phase:

Extension to Australian markets — McGrath Real Estate agent base
Expanded AskKen AI modules covering insurance policy guidance and advanced financial modelling
Business intelligence dashboard — appraisal volumes, lead conversion rates, and sales-to-property-management referral tracking
Further EMV model refinement with expanded suburb-level correlation data from new-build entries
Automated contact creation in the platform when new landlords are onboarded

Looking for a Similar AI Property or Real Estate Technology Solution?

Peritos Solutions specialises in AI-powered applications, machine learning valuation models, RAG chatbots, and cloud-native platforms on AWS — across New Zealand, Australia, USA, and India.

info@peritosolutions.com | +64-212579909 | www.peritossolutions.com