Richard Pallangyo · Data & AI engineer · Seattle
Writing about AI, data, and what makes them reliable.
I'm Richard, a data and AI engineer in Seattle. Field notes on shipping production systems: the agents, the pipelines underneath them, and the parts that never make the demo.
Notes on AI-assisted development
Patterns that have held up across four months of work with Claude Code.
A measured account of what working with AI coding tools at scale actually looks like. It covers the collaboration shape, what makes a draft good or bad, where the discipline goes, and the productivity questions I can and can't honestly answer.
Read itAI engineering
Shipping agents and LLM systems that hold up outside the demo: grounding, evaluation, and the failure modes nobody screenshots.
Data engineering
The pipelines and infrastructure underneath the models, the unglamorous plumbing that decides whether anything above it can be trusted.
Software & craft
How the work actually gets built: AI-assisted development, hard rebuild calls, and the patterns that survive contact with production.
When to abandon the low-code path
2026.04Why I rebuilt my procurement agent from scratch in week three of a four-month internship.
Anti-hallucination through tool grounding
2026.03A small experiment in forcing every claim from an LLM agent through a deterministic database query.
New writing on AI, data, and the craft of building it.
Occasional, considered, and free. No noise, just the next piece when it’s ready, straight to your inbox.
I also build things: production AI agents, data infrastructure, and a CRM platform I'm shipping. If you came to see the engineering rather than read about it, the selected work and a fuller about are a click away.