AI engineering · Chicago
I build AI agents that let people talk to their data.
Principal Data Analyst, AI-Enabled Analytics at Walmart. I build the agents, and the governed context underneath that makes their answers trustworthy. The LLM proposes; deterministic code decides.
Opens the live demo. Answers take 20–30 seconds.
Flagship · live
SQL RAG
Retrieval-augmented text-to-SQL on BigQuery. It retrieves similar example queries, writes SQL with Gemini 2.5, checks it, runs it and charts the answer. Every answer shows its work: the examples it used, the tables, the model, the tokens and the BigQuery cost.
- At Walmart
- 95%
- SQL accuracy
- At Walmart
- ~80%
- faster query creation
- This demo
- 20–30s
- question to chart
What I'm building now
Agents, and the governed context that makes them trustworthy
At Walmart. The work is internal, so there are no links.
18,700+
columns in an ontology and lineage layer
1,700+ tables, built by parsing 900+ production SQL jobs
400+
data requests closed by an autonomous Jira agent
plus a self-service analytics agent business teams use daily
6
MCP servers with ~75 agent tools
two drive web apps through a headless browser
400+
tests behind graded evals with safety traps
because an agent nobody trusts doesn't get used
Selected work
Projects
live demo · evals · document AI
DrawCheck: construction pay-application checker ↗
Checks a contractor's monthly bill (PDF, Excel, Word or a scan) before anyone pays it: the line math, retainage, change orders and last month's figures, citing the cell behind every problem. Scans are read by a vision model and OCR, and a number counts only when both agree. Caught a real line billed at 105% in a public city bill.
live · multi-agent · GCP
LabDrift: keeps Google Cloud labs current ↗
Reads Google Cloud's daily release notes, finds the course-lab steps they break, drafts a fix, has a second model critique it, and queues it for review. 134 verified fixes on Google's public training repo; deployed with Terraform on Cloud Run.
live · agents · semantic layer
MarketCase: live KPI agent on Polymarket ↗
Checks Polymarket's trading KPIs every hour. When one leaves its usual range, an agent investigates why and writes an answer where every number links to its query. Plus a daily morning read.
open source · agents · evals
Interview Prep: a job-search agent that never hits send ↗
Turns a job posting into a tailored resume, an apply packet and recruiter emails, built as Claude Code skills. It writes drafts and never sends them: outreach waits until I mark the role applied, and every number on a resume must come from a verified claim. I ran my own search on it (126 roles, 50+ applications), then split it into an installable template with behavior evals and a trace that explains each step.
data engineering
joinmap: join discovery ↗
Discovers valid single- and multi-hop joins across unfamiliar BigQuery databases from schema and data evidence, with SQL pushdown.
rag · best in show
Proposal RAG for FTI Consulting ↗
RAG over past proposals, adopted by FTI Consulting: ~30% faster drafting, +42% retrieval with adaptive chunking, +34% generation with query rewriting.
mcp
PFF MCP server ↗
Gives Claude access to Pro Football Focus premium stats through browser automation and first-party JSON APIs.
full stack
Prediction-market data workspace ↗
Kalshi and Odds API ingestion with credit-aware budgeting, FastAPI governance services and role-based React dashboards.
Experience
Download resume (PDF) →Walmart · Principal Data Analyst, AI-Enabled Analytics
Internal AI consultant for my org. Built a text-to-SQL copilot over Walmart BigQuery schemas (95% SQL accuracy, ~80% faster query creation), agents that monitor KPIs, and the ontology and MCP tooling underneath.
2024 – now
UChicago Data Science Institute · Graduate Student Researcher
Persona-driven multi-LLM chatbot (OpenAI + Gemini) for a staged donation experiment with 500+ participants.
2024
FTI Consulting · Capstone: RAG proposal generator
Deployed and adopted for client work. Best in Show, UChicago MS in Applied Data Science capstone.
2024
Innovare · Data Scientist
Risk model and dashboards across 10+ school districts: +7% retention, −15% course failures.
2022 – 2023
MS Applied Data Science, University of Chicago (4.0) · BS Information Systems & Economics, Loyola University Chicago