Featured Product Case Study 02 | AI-Assisted Decision Support / Workflow Systems

Property Acquisition Intelligence

A listing-intelligence and underwriting prototype that turns messy property information into sourced evidence, configurable acquisition rules, ranked decisions, and a smaller diligence queue.

Launch Synthetic Demo ↗ Read the Case Study Back to Portfolio
12Synthetic acquisition scenarios
6Critical evidence checks
3Decision states
0Live provider calls in public demo
What this case proves
I use AI and automation to structure ambiguity — but I keep the evidence, rules, uncertainty, and human decision visible.
DomainProperty acquisition / decision support
My RoleProduct strategy, UX architecture, decision modeling, prototype implementation
FocusEvidence extraction, underwriting, explainable scoring, diligence workflow
BuildBrowser prototype, synthetic feed, local persistence, transparent extraction logic
Problem

A listing is not a decision.

Property feeds are optimized for browsing, not acquisition judgment. Important facts are fragmented across descriptions, structured fields, public records, market estimates, title/deed information, inspection evidence, and operator assumptions.

The acquisition problem is to reduce that noise into a defensible sequence: What immediately disqualifies this asset? What evidence do I actually have? What is still unknown? What is the modeled basis and cash flow? What deserves diligence next?

Product question

How might I convert a large, inconsistent listing feed into a smaller queue of explainable opportunities without pretending uncertain data is trustworthy?

AI-Assisted UX Decision Support High-Data Interface Workflow Architecture
Operating Model

The product separates evidence collection from investment judgment.

01

Intake

Normalize a listing feed or accept raw listing text for analysis.

02

Evidence

Extract roof, HVAC, electrical, plumbing, lead, occupancy, rent, rehab and risk language with provenance.

03

Enrichment

Keep taxes, market rent, neighborhood, policy and future title/licensing sources distinct from listing claims.

04

Underwriting

Model total basis, operating allowances, net monthly cash flow and cash yield.

05

Diligence

Rank Buy / Diligence / Pass while exposing hard rejects, evidence gaps and next verification questions.

Decision Sequence

Hard gates first. Weighted judgment second.

01IngestListing feed or raw property copy enters a normalized acquisition record.
02ExtractRelevant claims are converted into structured evidence with source and confidence.
03EnrichExternal facts and operator estimates remain labeled separately from listing-language evidence.
04RejectFatal criteria such as ground rent, oil heat, excessive rehab, weak neighborhood or budget failure are applied first.
05UnderwriteCondition, compliance, rent, basis, cash flow, yield and evidence completeness create a comparable score.
06PrioritizeThe operator receives a smaller diligence queue, rationale, missing evidence and shortlist/export actions.
Trust Model

Unknown does not mean good.

A common failure mode in automated screening is to reward the absence of a warning as if it were positive evidence. I designed the evidence layer to keep missing facts visible and reduce confidence when critical information is not verified.

The interface distinguishes explicit listing evidence from structured/enriched data, and it shows confidence rather than hiding the logic behind an opaque AI verdict.

Critical evidence checks

  • Roof age / installation evidence
  • HVAC age / system evidence
  • Electrical condition
  • Plumbing condition
  • Lead documentation
  • Occupancy state
Interactive Prototype

Pressure-test the acquisition logic.

Change the operating criteria, filter for evidence gaps, inspect a ranked candidate, analyze raw listing copy, then shortlist and export a diligence queue. The public build is intentionally synthetic and source-agnostic.

property-acquisition-demo.html · synthetic recruiter build
Open full screen ↗
Design Decisions

Where the UX work created leverage.

Decision 01

Separate hard rejects from scoring

A fatal deal condition should not be averaged away by strong rent or condition. Disqualifiers run before the weighted score.

Decision 02

Expose provenance and confidence

Each extracted field retains the statement or source category behind it, so the operator can inspect why the system believes a fact.

Decision 03

Penalize incomplete diligence

Missing roof, HVAC, electrical, plumbing, lead or occupancy evidence reduces the score and creates a visible evidence-gap queue.

Decision 04

Keep enrichment distinct

Taxes, neighborhood, market rent, title/deed and inspection facts are modeled as separate source adapters instead of being falsely attributed to listing text.

Decision 05

Make the strategy configurable

The operator can change budget, one-asset vs. two-asset strategy, rehab tolerance, neighborhood floor and operating assumptions, then watch the queue re-rank.

Decision 06

Decouple live intake

The recruiter demo makes zero listing-provider calls. Production source connections sit behind adapters so source reliability can evolve without rewriting the acquisition workflow.

AI-Assisted UX

AI is the accelerator, not the hidden authority.

I used AI to accelerate product iteration, generate synthetic scenarios, pressure-test decision logic, structure evidence categories, and shorten the loop from product rule to executable prototype.

The public extraction behavior is intentionally transparent. A production system could place deterministic parsers, APIs, or language models behind the same evidence contract while preserving human review and source visibility.

Human judgment stays in control

The product does not claim to decide whether to buy a property. It decides what should be rejected, what deserves more evidence, and what should rise to the top of a human diligence queue.

Explainable AI Prototype Logic Rules Engine Evidence UX
Outcome

What the finished prototype demonstrates.

AI product thinkingUnstructured input becomes structured evidence without hiding uncertainty or provenance.
Decision architectureHard gates, weighted scoring and evidence completeness operate as distinct layers rather than one mystery number.
High-data UXPrice, basis, rent, rehab, condition, compliance, market and evidence state remain scannable in one ranked surface.
Workflow reductionThe output is a prioritized diligence queue rather than another list of properties to manually inspect.
Source-agnostic designProduction listing and enrichment providers can change behind adapters while the UX contract remains stable.
Public-safe proofSynthetic scenarios, isolated local storage and zero provider credentials make the product safe to inspect.

Public / Production Boundary

The public demo uses synthetic listings and deterministic extraction logic. It does not connect to Redfin, Zillow, MLS, public-record systems, banking data, private KBP records, or any production API. Production source selection and reliability are separate architecture decisions.

What recruiters should look for

Follow the decision contract.

Do not judge this case by the property domain alone. Look at how ambiguous input becomes evidence, how missing data is handled, how fatal rules differ from soft scoring, how source confidence is communicated, and how the product moves a user from feed noise to a smaller action queue.

Bottom line: Property Acquisition Intelligence is public evidence of the same capability my résumé and Workflow Systems page describe: use systems thinking, AI-assisted analysis, front-end-aware prototyping, and explicit decision logic to turn messy operational information into something people can evaluate and act on.