Sharing with the community since 2007
My personal corner of the web — writing, open-source projects, agents, datasets, and talks from two decades of building data platforms. True to form, the whole site is data too: every list here is a parquet file.
Latest on LinkedIn
All →
LinkedIn ↗postOct 25, 2026An AI function for SQL, one row at a time: the answers come back as new columns
In January 2025 I put an LLM inside a SQL editor. The answer was text. This is the implementation on top of the Pyodide foundation: the function, the working code and the demo.
LinkedIn ↗postOct 25, 2026Python in the browser, with Pyodide: the foundation for AI in SQL
I wanted to show AI in SQL, using Jev. For that I needed Python running next to DuckDB, in a place anyone can open without installing anything. Pyodide gave me that.
LinkedIn ↗articleOct 25, 2026Bank Statements to Cash-Flow Insight, A Data Pipeline in Databricks
Use case A small company gets its bank statements as PDFs every week and every month. This architecture turns those PDFs into one cash-flow view that finance, the founder and the investors can trust.
LinkedIn ↗postOct 24, 2026Jev in job-pilot: typed decisions in my open source job search agent
My open source job agent now asks Jev (TypeSafe AI) for its fuzzy decisions, and the dataset it publishes every day stays open.
LinkedIn ↗postAug 28, 2026Today was my last working day at Pentaho
Eleven years. Three acquisitions. Four names. One product. My journey with this product began in 2015 at Rokitt Inc., a small New Jersey startup building a machine-learning-driven…
LinkedIn ↗postAug 27, 2026Happy International Dog Day
🐾 Milo has been by my side since May, 2023 — quiet teammate on long workdays, stress reliever, and my daily reminder to slow down and enjoy the little moments. Some companions…
LinkedIn ↗postAug 21, 2026Every enterprise system remembers what happened
Very few can explain how it happened. Life sciences shows this gap at its sharpest. A clinical trial runs for years — protocols change, sites join, subjects enroll, adverse events…
LinkedIn ↗postAug 15, 2026I created my own digital brain as a knowledge graph, and it is already up and…
running on my laptop/server using Zep’s Graphiti + FalkorDB. I was inspired by Garry Tan’s GBrain project, but I took a very different approach and it is not just documents,…
LinkedIn ↗postAug 10, 2026AI Evals, Metrics and Rubrics are often discussed more as theory, but they…
become very important when we build real AI systems. Coming from Data Governance and regulated-industry experience, I have always seen PII identification as a good example.…
LinkedIn ↗postAug 9, 2026I don't open VSCode anymore
Everything I build now runs through the CLI. I've been living in the terminal since February. I picked up GitHub Copilot CLI but in April this year, I switched to Claude Code — no…
Recent blog posts
All →Building a Generative Q&A Engine with Semantic Search and Embeddings
BlogApr 22, 2025Building a Generative Q&A Engine with Semantic Search and Embeddings
In the age of AI-powered tools and intelligent systems, the ability to search, analyze, and generate insights from documents has become paramount.
Edge-Optimized GenAI Chat Web-UI for Ollama & Cloudflare AI models with Context Injection
BlogFeb 3, 2025Edge-Optimized GenAI Chat Web-UI for Ollama & Cloudflare AI models with Context Injection
It is a simple GenAI chat web interface built with Next.js that connects to both local Ollama and Cloudflare AI models.
Embedding LLM in SQL is simple!
BlogJan 27, 2025Embedding LLM in SQL is simple!
Inspired by Snowflake’s AI-driven analytics and MotherDuck’s recent implementation of SQL + LLM (Introducing the prompt() function), I explored LLM-powered Business Insights using DuckDB, embedding AI directly into SQL workflows for real-time data intelligence.
Data Pipeline Diagrams as Code
BlogJan 6, 2025Data Pipeline Diagrams as Code
Creating diagrams for data pipelines, workflows, and architectures is a routine task for many of us. Whether it's for internal presentations, client discussions, or technical documentation, the process can often feel repetitive and time-consuming.
Privacy Engineering with LLMs: Safeguarding PII While Enhancing Text with Privacy Shield
BlogDec 31, 2024Privacy Engineering with LLMs: Safeguarding PII While Enhancing Text with Privacy Shield
In the age of AI-powered tools and intelligent systems, the ability to search, analyze, and generate insights from documents has become paramount.
Lightweight HTML to PDF with Puppeteer: Simple PDF Export for Edge Deployments
BlogDec 27, 2024Lightweight HTML to PDF with Puppeteer: Simple PDF Export for Edge Deployments
This microservice is designed to address simple PDF export needs, making it ideal for generating blog articles, profile cards, and other lightweight use cases.
Projects
All →AI Agents Monorepo
Monorepo of Vercel Eve agents (API test generator, diagram generator, GitHub PR digest, LinkedIn cover generator) sharing a common runtime kit, plus the AI SDET Workbench slide deck.
largeOSSAIAgentsTypeScriptLive demoDocsClaimWise
Healthcare RCM synthetic data generator and data lakehouse demo monorepo — inspired by dbt's jaffle_shop.
largeOSSHealthcareData-EngineeringdbtTemplrGo
Lightweight developer platform with Lua serverless functions, SQL playgrounds, embedded BoltDB storage, and AI chat assistant. Config-driven, single-binary deployment.
largeOSSGoPlatformCMSLive demoDagster Data Pipelines
Collection of data engineering projects using Dagster to manage and orchestrate data pipelines.
largeOSSPythonDagsterData-Engineering