Work
Financial models, data infrastructure, AI systems, and operational platforms — built for real businesses solving real problems. Not mockups.
Open-source-derived registry of the AI compute chain's physical inputs
Built a global datacenter registry with per-field provenance — facilities, power, chips, cooling, and fiber modeled as a graph — plus a fully static map dashboard exposing the physical infrastructure behind the AI buildout.
View case studyThe flagship priced index for the physical AI-infrastructure stack
Built a market-intelligence engine that ingests surplus, channel, and public data across the AI buildout supply chain and publishes four weekly indices — compute, interconnect, power, and facility — each a per-component rebased composite with every input cited to a source trust tier and a versioned methodology.
View case studyGeospatial radar for growth-corridor land position in North Texas
Built a PostGIS-backed corridor intelligence engine that screens entire Texas counties for development-relevant land — measuring road frontage, FEMA flood exposure, parcel geometry, utility service-area position, and jurisdiction regime — and watches public infrastructure signals (CCN amendments, city agendas, school growth, TxDOT access) as they move.
View case studyHow honest trade booking turned a promising backtest into a 'do not trade' decision
A systematic Treasury-futures curve strategy backtested at a respectable Sharpe over 33 years — until honest 3-leg trade booking revealed most of the 'edge' was an accounting artifact and the strategy quietly lost to T-bills. The interesting result isn't the strategy; it's the discipline that killed it.
View case studyBuy-side intelligence for surplus equipment acquisition
Built the acquisition layer for a surplus equipment operation — a 26-source scraper network that surfaces underpriced auction lots, 17 per-vertical fair-value models, and a full profit-model cost stack that backs out the maximum responsible bid for a target margin before a dollar is committed.
View case studyNOI variance narrative engine for multifamily operations
Built a local-first Rust harness that explains why a property's NOI missed or beat budget — computing a deterministic revenue-expense-NOI bridge, ranking the GL accounts driving the gap, and writing an evidence-backed, plain-English variance narrative with every claim traced to its source row.
View case studyLocal-first economic and corridor intelligence for North Texas
Built a local-first intelligence system that turns public-source briefs, permit portals, RFP notices, and infrastructure signals into a structured, searchable archive of civic and corridor intelligence across the North Texas / Texoma region.
View case studyHuman-centered civic intelligence under an alignment protocol
Built a local-first civic friction-mapping and decision-support system for North Texas economic activity — engineered under a binding alignment protocol that informs founders and local operators first, surfaces de-identified process friction back to public stewards, and refuses to turn public records about named people into scores or lead lists.
View case studyA deterministic underwriting engine for institutional multifamily acquisitions
Built a deterministic underwriting engine that ingests offering memorandums, rent rolls, and T12 financials and produces full month-by-month cashflow, IRR, DSCR, and exit-cap analysis — with every output reconciled against an institutional model and traceable back to its source documents.
View case studyLender-driven origination sourcing and public-record monitoring
Built a deterministic data platform that sources and monitors fragmented Texas county public records, normalizing them across systems into a single provenance-tracked daily watchlist that supports human-led real estate credit origination decisions.
View case studyAI-native relationship intelligence CRM for a private capital operator
Built an AI-native relationship intelligence system that ingests Microsoft 365 email, calendar, and contacts into a unified data layer — then surfaces follow-ups, relationship health, and next-best-actions through a conversational AI interface instead of traditional CRUD screens.
View case studyPod-grade multifamily REIT financials, fully source-traced
Built an auditable database of public multifamily REIT supplemental disclosures (MAA, UDR, CPT, EQR, AVB, ESS, INVH, AMH) — extracting same-store NOI margin, capex, and capital-structure metrics that SEC XBRL doesn't expose, every number traceable to the exact page of the exact filing.
View case studyA transparent, rules-based screen for overlooked small-cap bank equities
Built a fully auditable screener that ranks U.S. listed community banks on price-to-tangible-book, capital strength, credit quality, and insider alignment — turning a 247-name universe into a short list of 129 names that clear seven hard gates, each traced to FFIEC Call Reports and SEC filings.
View case studyAI-powered multifamily market research platform
Built an agent-driven platform that produces institutional-quality multifamily market studies, combining public data pipelines with AI analysis and compliance-first reporting.
View case studyQuantitative decision system for financial markets
Designed and built a multi-strategy algorithmic trading platform with rigorous risk management, walk-forward backtesting, and full audit trail from signal to execution.
View case studyPortfolio intelligence platform for a $140M multifamily operation
Built the operational backbone for a $140M multifamily real estate portfolio — a full-stack dashboard ingesting rent rolls, comp analysis, turnover reports, and 500K+ general ledger transactions into real-time unit economics and asset management intelligence.
View case studySystem dynamics modeling for sustainable agriculture
Built a weather-driven simulation engine that optimizes paddock rotation schedules for a North Texas ranching operation, balancing forage growth, soil moisture, and carrying capacity.
View case studyState-space estimation for real estate market timing
Developed a novel state-space estimation system that tracks market cycle dynamics through spiral coordinates, combining Kalman filtering with Texas multifamily market data for quantitative cycle positioning.
View case studyReusable geospatial infrastructure for CRE analysis
Developed a shared Python library providing PostGIS database management, Census data ingestion, TIGER/Line shapefile handling, and drive-time routing for commercial real estate spatial analysis.
View case studyLand productivity analysis for urban renewal
Built a data-driven system that identifies parcels with rising redevelopment pressure by analyzing the relationship between land value, improvement value, and time using public tax records and GIS.
View case studyFrom spreadsheets to engineered forecasting
Replaced a manual Excel-based workflow with an automated cashflow forecasting and liquidity engine for a multi-property real estate investment fund.
View case studyPython cashflow engine for complex commercial assets
Built a comprehensive underwriting toolkit for mixed-use commercial real estate combining office, retail, and multifamily components — replicating core Argus functionality without the subscription cost.
View case studyLocal-first digital newspaper for Texoma
Bootstrapped launch of a fast, legible, SEO-friendly local news platform serving Cooke County.
View case study