Making home search less overwhelming - without cutting the agent out - hero image

Cotality / OneHome

Concept

Making home search less overwhelming - without cutting the agent out

Cotality partnered our capstone team with OneHome, the portal that connects homebuyers with their real estate agents, and asked how AI should change home search. Two quarters of research pushed us off "better AI search" and onto a sharper problem: buyers are drowning in content-dense listings, and agents lose hours to work a good summary could do. We designed two AI features against that and tested them with 21 homebuyers and agents.

Quick scan

Cotality asked how AI should change home search on OneHome. Research reframed it: make search less overwhelming for buyers, and give agents back the time repetitive work eats.
Four-person capstone across two quarters - spring research was driven by a teammate; the reframe, the two feature concepts, and the call to keep the agent central were made together. My own focus was the AI chat layer - the piece I took furthest from concept to final design - plus alternate concepts and evaluation across both features.
An idea I explored but that didn't survive to final designs: have the AI show its work - link every recommendation back to the listing details or criteria behind it - so trust came from being checkable, not just from sounding confident.
We designed and tested two features: an AI Preference Prioritization Summary (a % match, with what fits and what's missing) and an AI Comparison Summary (must-haves vs. nice-to-haves across two listings).
21 participants across two rounds - moderated on medium-fidelity, then unmoderated with 8 active homebuyers and 5 agents on high-fidelity. Every tester explained the % match feature unprompted; the one consistent failure, a horizontal-scroll pattern nobody found, got designed out.
Done and delivered - but still a concept, not a shipped product. We only ever designed the buyer-facing view; the agent's own side of the flow is the gap we'd close next.

Team

Cindy Chiang, Shawn Farnum, Trinah Maulion, Isabel Schnebelie

Role

Drove the AI chat layer from concept to final design; research, concept design, and evaluation across both features

Timeline

22-week capstone across two quarters · UC Irvine, HCI & Design

Status

Completed - final designs and report delivered to Cotality

Cotality asked that the concept screens stay off the open web - the process and findings below are public. Unlock to see the actual screens, or email me for the password.

Overview

OneHome is Cotality's real estate portal, and the thing that makes it different from the big public listing sites is that it connects a homebuyer to an actual agent. Their brief - Project Evolve - asked how AI should change search on OneHome without breaking that.

Spring quarter was research. Summer was design and evaluation, roughly ten weeks. We scoped it hard: the homebuyer search and comparison experience only. Sellers, commercial real estate, Cotality's other products, and production engineering were all explicitly out.

Four of us worked on it, and the work was genuinely shared - a teammate drove much of the spring research, and the reframe, the two feature concepts, and the principles we held ourselves to were argued out together.

Where I fit on this team

The two primary features were shared across all four of us, with everyone weighing in as the concepts and designs evolved. My deepest ownership was the AI interaction layer inside both - Ask AI, Summarize, Suggested Questions - which I carried from concept through final design, with the rest of the team shaping it along the way like everything else. I also built alternate concepts for the Preference Summary and Comparison Summary; neither became the final layout, but pieces of that thinking made it into what shipped. Separately, I concepted a preference-overlay feature - letting buyers thumbs-up or thumbs-down individual insights instead of restating one blanket preference - that never made it past the sketch stage; it's on the list of what we'd build next if we had more time.

The instinct I try to bring to a team like this is less about owning one polished screen and more about catching what everyone else is boxed into. Four people converging on the same kind of solution is a real risk on a capstone team, and I look for the question nobody's asked yet - the clearest example is in the AI chat layer below.

What the designs were built on

competitor platforms analyzed, focused on how each one implements AI

290 + 84

homebuyer + real estate agent survey responses, US and Canada

usability testing participants across two rounds

design iterations, low-fidelity through final

The reframe

We started with a question that already assumed its own answer: how might we strengthen collaboration by incorporating AI search tools into OneHome? Research moved us off it. Buyers weren't asking for a smarter search box - they were overwhelmed by content-heavy listings with no sense of what mattered to them, and they mostly used AI to understand the homebuying process, not to find homes. Agents weren't asking for AI search either; they wanted the repetitive work back - paperwork, emails, scheduling, manually cross-referencing listings before sending options to a client.

So the question became: how might we strengthen homebuyer-agent collaboration by making the search process less overwhelming for buyers and reducing the repetitive workflows that consume agents' time? We handed Cotality three recommendations out of spring. They had already started building the first one - expanded filters plus conversational search - so summer went to the other two.

The rules we designed against

Six principles came out of research. Four of them did most of the deciding:

AI should assist, not override - every AI feature stays optional and sits inside the existing workflow instead of taking it over.
Support over stress - reduce complexity so buyers feel confident and agents have something concrete to guide with.
Surface what's important - prioritize the information relevant to this specific buyer instead of showing everything at equal weight.
Preserve the personal - this is one of the biggest decisions in someone's life, and the platform should help them navigate it on their own terms.

How we got to a tested design

Low-fidelity sketches
Both features started as sketches so we could throw away directions cheaply before committing to any one layout.
Moderated testing, medium-fidelity
8 participants from our network, on deliberately unfinished wireframes. Medium fidelity was the point - we wanted the why behind a reaction while the designs were still cheap to change.
Unmoderated testing, high-fidelity
8 active homebuyers and 5 real estate agents recruited through CloudResearch Connect, thinking aloud with nobody there to help. This round asked a different question: are these designs self-explanatory without us in the room?
Final iteration
The last pass fixed what testing actually broke - clearer groupings, more intuitive icons and color, and one interaction pattern removed entirely.

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

Feature 1: AI Preference Prioritization Summary

A listing gets a match score, and under it two expandable groups: what matches your top preferences, and what's missing from them. Color-coded, scannable, collapsed by default. The same information routes back to the buyer's agent, so the agent stays current on priorities that shift mid-search instead of finding out on a tour.

The unmoderated round settled the main question: every single tester correctly explained what the % match feature did on their own, unprompted, usually by pointing at a specific miss like hardwood floors. Asked whether they'd use it for real, all of them said yes. One pattern failed consistently, though - we'd put Suggested Questions in a horizontal scroll, and testers simply didn't find it.

I didn't realize on this test I could also scroll right and left on that bottom portion. I thought it was more of a preview... you can only see the first few letters.

Homebuyer, unmoderated usability test - the finding that changed the final layout

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

Feature 2: AI Comparison Summary

Two listings side by side, one flagged as the best match, and a How They Compare panel that scores both against the buyer's own criteria - split into must-haves and nice-to-haves, with checks and X's per row. The point is that the criteria are the buyer's, not a fixed preset list. Agents do this comparison by hand today before sending a client options, so automating it buys back time they'd rather spend with the client.

In testing, every user found the must-have and nice-to-have tables intuitive and the check marks fast to scan. Agents read the feature differently than buyers did: less as a shortcut, more as a source of talking points and better questions to walk a client through.

Especially helpful for first-time homeowners... while it's more than likely they'd be working with a real estate agent, having this feature helps them consider the questions they need to be asking.

Homebuyer, unmoderated usability test

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

Feature 3: the Ask AI layer

Ask AI, Summarize, and Suggested Questions are one shared component embedded in both features rather than a separate chatbot destination - the piece where I had the most direct concept-to-design ownership, with the rest of the team weighing in as it evolved. Testing shaped it twice: users - first-time buyers especially - told us a blank prompt left them with no idea what to ask, and the label we'd used, "Ask Me Anything," left people unsure who they were even talking to. So the final version leads with suggested questions and states plainly that the responses are AI-generated.

One direction I explored in mid-fi concepts never made it into the final design or the report: having every AI answer link back to what actually produced it - the listing details behind a % match, the criteria behind a recommendation - instead of just asserting a confident summary. Buyers and agents were being asked to trust an AI's judgment on one of the biggest purchases of their life, and I didn't think that trust should ride on tone alone; it should be checkable. It didn't survive scope and time - the chatbot got less iteration than the other two features - but it's the same instinct behind the preference overlay: make the AI show its work, not just assert it.

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

What testing actually taught us

Four things came up across both features, in both rounds:

Visual hierarchy, not information volume, decided whether people trusted a feature. Given the same content in different layouts, participants consistently chose the clearest one.
People want a guided way in, not an open prompt. Suggested questions weren't a nicety - they were what made engaging the AI feel possible for buyers who didn't know where to start.
Labels are load-bearing. "Ask Me Anything" was ambiguous enough to cost trust; naming the thing precisely was a design fix, not a copy edit.
Time saved isn't the value - relevance is. Some users wanted the summary tied more tightly to their own criteria, because generic output makes the time-saving feel superficial.

This feature would be very useful for me working with a client because it could help me give a main summary of the house and it could also help them.

Real estate agent, unmoderated usability test

Where this leaves Cotality

Public listing platforms are capturing homebuyers earlier and earlier with their own AI features, which puts pressure on Cotality to keep pace without giving up the thing that makes OneHome different: the agent relationship at the center of it.

Both quarters of research pointed the same direction. Buyers want AI to save time and lower stress. Agents want it to clear repetitive work off their plate. Neither group wants AI to become the default experience - they want it available on their own terms. That's what these two features give Cotality a way to build: AI that deepens the buyer-agent relationship instead of commoditizing it.

Limitations

Three real ones, worth stating plainly:

Ten weeks for the back half of the double diamond bought us three design iterations and two testing rounds across two features. More time would have meant more iteration and more edge cases found.
21 participants is a small sample against OneHome's actual user base. Cotality was interested in a larger one; it wasn't feasible on our time and budget.
We didn't collect participant demographics during testing, which means we can't say anything about demographic-specific patterns in what we saw.

What's next - and what we never got to

The most useful next move is more testing: validate the final iteration against a larger, more diverse sample than 21 people from our networks and CloudResearch.

The honest gap is the agent's side. Both features send information back to the agent, but our prototype only ever covers the public-facing view. We never designed or tested how a buyer's activity actually surfaces to an agent in their own interface - that's a whole half of the flow we're asserting rather than showing.

Early conversations with Cotality also touched on improving the information flow between buyer and agent directly, which we couldn't test this phase. I sketched one concept for it: after a buyer favorites a listing, a quick overlay asks what specifically mattered about it, then lets them thumbs-up or thumbs-down individual insights - commute, HOA cost, yard, school zone - more of this, less of that, instead of restating one blanket preference. That signal would feed both their own future summaries and their agent's view. It's a sketch, not a finding.

On my own list: an actual working prototype of the Ask AI layer. The course never called for that level of fidelity, but I want to see the sourcing behavior and suggested questions actually run, not just click through static screens - that's the next thing I'd build for this portfolio, separate from the course deliverable.

Screenshot on request

Cotality asked that concept screens stay off the open web - unlock above, or email me for the password.

Locked

What this was actually about

We came in asking what AI should do for home search. The more useful question turned out to be what it shouldn't. Once we stopped trying to make the AI decide and let it do the narrower job - organize, prioritize, explain - the designs got clearer, and testing backed them.

The final direction for OneHome is a supportive layer, not a replacement: AI that hands a buyer the questions worth asking, and hands their agent the context to answer them.

Back to all work Get in touch

Making home search less overwhelming - without cutting the agent out

Overview

Where I fit on this team

What the designs were built on

The reframe

The rules we designed against

How we got to a tested design

Low-fidelity sketches

Moderated testing, medium-fidelity

Unmoderated testing, high-fidelity

Final iteration

Feature 1: AI Preference Prioritization Summary

Feature 2: AI Comparison Summary

Feature 3: the Ask AI layer

What testing actually taught us

Where this leaves Cotality

Limitations

What's next - and what we never got to

What this was actually about

Overview

Where I fit on this team

What the designs were built on

The reframe

The rules we designed against

How we got to a tested design

Low-fidelity sketches

Moderated testing, medium-fidelity

Unmoderated testing, high-fidelity

Final iteration

Feature 1: AI Preference Prioritization Summary

Feature 2: AI Comparison Summary

Feature 3: the Ask AI layer

What testing actually taught us

Where this leaves Cotality

Limitations

What's next - and what we never got to

What this was actually about