LandOnEarth
AI-powered decision system translating lifestyle preferences into structured home-matching intelligence.
AI Matching
AI Matching
Conversational UX
Conversational UX
Decision Systems
Decision Systems
Overview
LandOnEarth is an AI-powered real estate platform designed to support high-stakes home decisions through structured, explainable intelligence.
As Product Design Lead, I translated the original vision into a scalable decision-support system — defining the core signal architecture, interaction model, and foundational UX patterns that anchored the platform’s evolution.
Alongside product development, I established the initial product and brand identity framework to ensure the AI-driven experience communicated clarity, trust, and decision confidence from day one.
Role
Product Design Lead
Defined the AI-driven HomeMatch system architecture and signal framework
Designed conversational onboarding and property alignment workflows
Established scalable UX foundations and reusable component systems
Partnered with founders and engineering to operationalize machine learning outputs
Led and mentored design contributors as the product matured
Established foundational product and brand identity systems aligned with platform positioning
Product Design Lead
Defined the AI-driven HomeMatch system architecture and signal framework
Designed conversational onboarding and property alignment workflows
Established scalable UX foundations and reusable component systems
Partnered with founders and engineering to operationalize machine learning outputs
Led and mentored design contributors as the product matured
Established foundational product and brand identity systems aligned with platform positioning
Product Design Lead
Defined the AI-driven HomeMatch system architecture and signal framework
Designed conversational onboarding and property alignment workflows
Established scalable UX foundations and reusable component systems
Partnered with founders and engineering to operationalize machine learning outputs
Led and mentored design contributors as the product matured
Established foundational product and brand identity systems aligned with platform positioning
Problem
Real estate decision-making is fragmented and opaque.
Buyers struggle to translate lifestyle needs into structured criteria.
Agents rely on static filtering tools that overlook nuance.
AI-driven recommendations often lack transparency, reducing trust.
The challenge was not simply implementing AI — it was designing a system that made AI legible, actionable, and embedded into real-world decision workflows.
Real estate decision-making is fragmented and opaque.
Buyers struggle to translate lifestyle needs into structured criteria.
Agents rely on static filtering tools that overlook nuance.
AI-driven recommendations often lack transparency, reducing trust.
The challenge was not simply implementing AI — it was designing a system that made AI legible, actionable, and embedded into real-world decision workflows.
Real estate decision-making is fragmented and opaque.
Buyers struggle to translate lifestyle needs into structured criteria.
Agents rely on static filtering tools that overlook nuance.
AI-driven recommendations often lack transparency, reducing trust.
The challenge was not simply implementing AI — it was designing a system that made AI legible, actionable, and embedded into real-world decision workflows.
Approach
I structured LandOnEarth as a cohesive decision-support architecture built across three core layers:
Signal Capture
Conversational AI translates qualitative lifestyle preferences into structured, quantifiable signals.
Profile Synthesis
Signals are synthesized into a dynamic HomeMatch profile that defines decision criteria at a system level.
Property Alignment
Listings are ranked by quantified lifestyle alignment, prioritizing overall fit over isolated features.
Guiding principles included:
Design for decisions, not data
Make AI explainable and trustworthy
Reduce cognitive load in complex workflows
Establish scalable design and identity foundations early
By aligning product architecture and brand expression, the system communicated intelligence and reliability as core attributes of the experience.
I structured LandOnEarth as a cohesive decision-support architecture built across three core layers:
Signal Capture
Conversational AI translates qualitative lifestyle preferences into structured, quantifiable signals.
Profile Synthesis
Signals are synthesized into a dynamic HomeMatch profile that defines decision criteria at a system level.
Property Alignment
Listings are ranked by quantified lifestyle alignment, prioritizing overall fit over isolated features.
Guiding principles included:
Design for decisions, not data
Make AI explainable and trustworthy
Reduce cognitive load in complex workflows
Establish scalable design and identity foundations early
By aligning product architecture and brand expression, the system communicated intelligence and reliability as core attributes of the experience.
I structured LandOnEarth as a cohesive decision-support architecture built across three core layers:
Signal Capture
Conversational AI translates qualitative lifestyle preferences into structured, quantifiable signals.
Profile Synthesis
Signals are synthesized into a dynamic HomeMatch profile that defines decision criteria at a system level.
Property Alignment
Listings are ranked by quantified lifestyle alignment, prioritizing overall fit over isolated features.
Guiding principles included:
Design for decisions, not data
Make AI explainable and trustworthy
Reduce cognitive load in complex workflows
Establish scalable design and identity foundations early
By aligning product architecture and brand expression, the system communicated intelligence and reliability as core attributes of the experience.
Key Design Decisions
Designing trust into an AI-driven recommendation. The central risk in an AI-powered home matching product is that users don't trust the output — especially when the stakes are as high as a home purchase. An unexplained recommendation, no matter how accurate, creates anxiety rather than confidence. The critical design decision was to make the reasoning behind every recommendation visible: surfacing which lifestyle signals drove a property's match percentage, and which factors were creating misalignment. This transparency wasn't just a UX feature — it was the mechanism that made the AI feel like a decision-support tool rather than a black box.
Converting qualitative lifestyle preferences into structured data without losing nuance. The core technical challenge was that the signals that actually drive good home decisions — "I want to live somewhere walkable but quiet," "we have two dogs and a toddler" — are inherently qualitative and conversational. The design decision was to build a conversational onboarding model that gathered these signals in natural language and translated them into a structured profile behind the scenes, rather than forcing users into static filter inputs that would strip the nuance out. The constraint this solved was that traditional search UI (beds/baths/price) systematically excludes the signals that most predict long-term satisfaction.
Designing for real estate agents as a parallel user, not an afterthought. Early in the project it became clear that buyers rarely navigate high-stakes home decisions alone — agents are almost always in the loop. Rather than designing purely for the end buyer and hoping agents would adapt, I architected the information model to be legible and useful to agents reviewing a client's HomeMatch profile. This meant the system needed to communicate not just recommendations, but the reasoning behind them in language an agent could use in a conversation with their client.
Designing trust into an AI-driven recommendation. The central risk in an AI-powered home matching product is that users don't trust the output — especially when the stakes are as high as a home purchase. An unexplained recommendation, no matter how accurate, creates anxiety rather than confidence. The critical design decision was to make the reasoning behind every recommendation visible: surfacing which lifestyle signals drove a property's match percentage, and which factors were creating misalignment. This transparency wasn't just a UX feature — it was the mechanism that made the AI feel like a decision-support tool rather than a black box.
Converting qualitative lifestyle preferences into structured data without losing nuance. The core technical challenge was that the signals that actually drive good home decisions — "I want to live somewhere walkable but quiet," "we have two dogs and a toddler" — are inherently qualitative and conversational. The design decision was to build a conversational onboarding model that gathered these signals in natural language and translated them into a structured profile behind the scenes, rather than forcing users into static filter inputs that would strip the nuance out. The constraint this solved was that traditional search UI (beds/baths/price) systematically excludes the signals that most predict long-term satisfaction.
Designing for real estate agents as a parallel user, not an afterthought. Early in the project it became clear that buyers rarely navigate high-stakes home decisions alone — agents are almost always in the loop. Rather than designing purely for the end buyer and hoping agents would adapt, I architected the information model to be legible and useful to agents reviewing a client's HomeMatch profile. This meant the system needed to communicate not just recommendations, but the reasoning behind them in language an agent could use in a conversation with their client.
Designing trust into an AI-driven recommendation. The central risk in an AI-powered home matching product is that users don't trust the output — especially when the stakes are as high as a home purchase. An unexplained recommendation, no matter how accurate, creates anxiety rather than confidence. The critical design decision was to make the reasoning behind every recommendation visible: surfacing which lifestyle signals drove a property's match percentage, and which factors were creating misalignment. This transparency wasn't just a UX feature — it was the mechanism that made the AI feel like a decision-support tool rather than a black box.
Converting qualitative lifestyle preferences into structured data without losing nuance. The core technical challenge was that the signals that actually drive good home decisions — "I want to live somewhere walkable but quiet," "we have two dogs and a toddler" — are inherently qualitative and conversational. The design decision was to build a conversational onboarding model that gathered these signals in natural language and translated them into a structured profile behind the scenes, rather than forcing users into static filter inputs that would strip the nuance out. The constraint this solved was that traditional search UI (beds/baths/price) systematically excludes the signals that most predict long-term satisfaction.
Designing for real estate agents as a parallel user, not an afterthought. Early in the project it became clear that buyers rarely navigate high-stakes home decisions alone — agents are almost always in the loop. Rather than designing purely for the end buyer and hoping agents would adapt, I architected the information model to be legible and useful to agents reviewing a client's HomeMatch profile. This meant the system needed to communicate not just recommendations, but the reasoning behind them in language an agent could use in a conversation with their client.
Impact & Outcomes
The platform is live with early users actively engaging with the AI-driven onboarding flow, with initial behavioral data being collected to inform continued iteration.
2 design patents filed supporting the HomeMatch system architecture
Live platform with early users completing conversational onboarding and receiving ranked property recommendations
Initial engagement signals validating the core lifestyle-to-property alignment model
Scalable UX foundations supporting continued product iteration
The patents reflect that the HomeMatch interaction system was novel enough to merit intellectual property protection — a strong signal of the foundational design work that anchored the platform.
The platform is live with early users actively engaging with the AI-driven onboarding flow, with initial behavioral data being collected to inform continued iteration.
2 design patents filed supporting the HomeMatch system architecture
Live platform with early users completing conversational onboarding and receiving ranked property recommendations
Initial engagement signals validating the core lifestyle-to-property alignment model
Scalable UX foundations supporting continued product iteration
The patents reflect that the HomeMatch interaction system was novel enough to merit intellectual property protection — a strong signal of the foundational design work that anchored the platform.
The platform is live with early users actively engaging with the AI-driven onboarding flow, with initial behavioral data being collected to inform continued iteration.
2 design patents filed supporting the HomeMatch system architecture
Live platform with early users completing conversational onboarding and receiving ranked property recommendations
Initial engagement signals validating the core lifestyle-to-property alignment model
Scalable UX foundations supporting continued product iteration
The patents reflect that the HomeMatch interaction system was novel enough to merit intellectual property protection — a strong signal of the foundational design work that anchored the platform.
Predictive insights and buyer context brought together into a single decision-support experience.
Conversational AI captures lifestyle, family, and activity preferences, transforming qualitative input into a structured HomeMatch profile that defines what “the right home” actually means for each user.
Properties are ranked by HomeMatch percentage, prioritizing overall lifestyle fit based on family needs, pets, and activities—helping users evaluate tradeoffs and focus on the homes most aligned with how they actually live.
Let’s build intelligent systems together.
Open to senior product design and leadership opportunities across AI, infrastructure, and complex platforms.