Blog

Essays on agentic systems, AI engineering, startups, and the craft of building.

A blank ruled index card with an arrow and a stack of order slips covered in tally marks, inside a dashed boundary with a check mark; below, white tulips in a kraft-paper cone

Oct 25, 2026 · 5 min read

What is AI?

Sam wants to send Elena tulips for her birthday. The flower-delivery site shows him roses first. What part of that is AI? The first of eight short posts on how AI works.

#ai-literacy #ai #agents

A navy ledger kept inside a dashed boundary with a check mark, beside loose and crumpled paper copies outside it

Oct 6, 2026 · 10 min read

Is your data layer ready for agents? The case for Lakebase

Agents need a disposable workspace and a durable record. Here's where Databricks Lakebase fits, in plain terms, and what it still leaves to you.

#agents #databases #lakebase #postgres #production

A grid of nine practice cutting boards, some messy; one clean board inside a dashed boundary with a check mark, and a padlocked box beside the grid

Sep 29, 2026 · 7 min read

When the database's newest user is an agent

When a whole company books travel through agents, the database gets a new kind of user: many, fast, and often wrong. What that asks of the data layer, and why branching alone isn't enough.

#agents #databases #dba #branching #production

An open index-card box; one card pulled out and kept inside a dashed boundary, with a boarding pass clipped to it and a check mark

Sep 22, 2026 · 5 min read

What an agent remembers

An agent books your flight, then crashes before writing it down. When it restarts, does it book again? What an agent remembers, and why some of it has to survive a crash.

#agents #agent-memory #databases #production

Two company ID badges, one for a person and one for an agent, each with the same company credit card, inside one dashed boundary

Sep 15, 2026 · 10 min read

What is an enterprise agent?

An enterprise agent isn't simply a model with tools. It's a system that pursues delegated goals, takes consequential actions, works within defined authority and keeps a clear line of accountability.

#agents #enterprise #architecture #production

An open journal kept inside a dashed boundary with a check mark, beside a printout of code and a pencil

Mar 9, 2026 · 14 min read

Your code survives the session. Your reasoning doesn't.

A practical guide to a personal journaling system for AI-assisted development: a Claude Code skill and a hook that capture the reasoning your code can't.

#ai-engineering #claude-code #developer-tools #best-practices

A row of five grey file folders; only one has a written label, and it sits inside a dashed boundary with a check mark

Mar 4, 2026 · 8 min read

Building the AI-ready data platform

Capable agents can still fail on stale or ambiguous data. What an AI-ready analytical platform needs, and why I favour a lakehouse foundation.

#ai-engineering #agents #data-engineering #lakehouse #production

A spread of many index cards heading for a narrow slot in a small navy box, with only a few through to a neat stack beyond it

Feb 18, 2026 · 7 min read

Data is the bottleneck in the agentic era

Agents need dependable data, and they create records of their own. Why I think data delivery becomes the constraint once the model can do the job.

#ai-engineering #agents #data-engineering #production

A fresh open notebook and pencil inside a dashed boundary with a check mark, beside a stack of older closed notebooks

Feb 14, 2026 · 3 min read

Starting over, on purpose

Why I rebuilt this site from scratch, and what I plan to write about next.

#meta #ai-engineering