Lead Business Analyst · Data Operations
Building AI-powered analytics systems that help organizations make better decisions.
I lead a team of analysts at Article, building the data infrastructure that powers decisions across ecommerce, merchandising, and operations. But I'm not interested in just building more dashboards.
I'm building AI assistants — systems that let anyone in the business query enterprise data using natural language. Systems that replaced 20+ static reports with 100+ weekly AI-driven conversations.
My background spans analytics engineering, experimentation, BI, and data modeling. My focus is the future: AI-native analytics workflows.
Dashboards are artifacts. I build data products — trusted, versioned, discoverable systems that evolve with the business.
Natural language is the new query language. I build AI interfaces that let any team member interrogate enterprise data without SQL.
Great analytics doesn't end at insight — it closes the loop into action. I design systems that automate the path from data to decision.
Each project is a system — designed to outlast any single report or query.
Teams relied on analysts to answer every data question. Dashboard sprawl meant 20+ reports, each requiring maintenance and context.
Built AI assistants ("Genies") on Databricks that allow any team to query curated enterprise datasets using plain English. Each Genie is scoped to a business domain — ecommerce, inventory, ops — with tuned prompts and trusted data models underneath.
Presented "Beyond the BI Ticket: From Reports to Conversations" to a packed audience of 250+ data leaders — making the case for AI-native analytics and conversational data access over static dashboards.
Beyond the BI Ticket: From Reports to Conversations · Databricks AI Day
Full room · 250+ attendees · Databricks AI Day Vancouver, March 2026
This is a simulation of the AI analytics assistant I built on Databricks. Ask a business question — Genie queries the data and responds in plain English.
Simulated demo · Real Genie runs on Databricks with live enterprise data
Short thoughts on the future of analytics, AI, and decision systems.
Static dashboards are artifacts of a world where data was hard to access. In a world with LLMs, the interface is a question. The answer is a query. The dashboard is just the fallback.
Hover to read more ↓
Teams obsess over beautiful visualizations and miss the point. Analytics value is in the decision it enables, not the dashboard it produces. Build for action, not for insight theater.
Hover to read more ↓
The skills that make a great data analyst — understanding data semantics, knowing what question is actually being asked — are exactly the skills that make a great prompt engineer.
Hover to read more ↓
You can build the most sophisticated AI assistant in the world. If the underlying data isn't trusted, your AI is just a confident liar. Data trust is the foundation everything else sits on.
Hover to read more ↓
In experimentation, we always fought to keep teams focused on one primary metric. Everything else — the curiosity clicks, the tangential signals — we called intellectual tourism. Curiosity without commitment.
But intellectual tourism was never the real problem. Analyst bandwidth was.
Conversational AI changes that entirely. When anyone can ask any question instantly, curiosity becomes cheap. The tourism is finally free — and we should be designing systems that enable it, not policing it.
Hover to read more ↓
Vibe coding let developers ship by feel — prompt, iterate, trust the model. Analytics is next.
But there's a catch nobody is saying loudly enough. Bad code breaks visibly. A wrong analytics answer looks identical to a right one — confident, formatted, fast.
The floor of vibe analytics isn't the AI model. It's governance. Semantic layers, certified datasets, curated contexts. The teams that win won't have the best models — they'll have the most trustworthy foundations underneath them.
Hover to read more ↓
The tools and technologies behind the systems I build.
Interested in AI-driven analytics systems, conversational data products, or building decision infrastructure? I'd love to connect.