I stopped writing about data. Here’s what brought me back.

I published my last Sanity Check in October 2023. Then I went quiet.

Not because I ran out of things to say — but because the ground was shifting under data engineering so fast that I wasn’t sure what was solid anymore.

The Silence

Here’s what I remember about late 2023: everyone had opinions. dbt was going through its identity crisis. Every data vendor on earth suddenly had an “AI-powered” something. LinkedIn was drowning in hot takes about whether analytics engineering was dead, alive, or just resting.

I had opinions too. But writing with conviction requires some amount of confidence that you’re not going to look like a fool in six months. And honestly? I wasn’t confident. The noise was deafening and the signal was thin. So I stepped back, kept consulting, and watched.

What Changed

Something shifted in the last year that I can’t ignore anymore.

Agentic AI isn’t another rebrand of the same hype cycle. It’s actually changing who consumes your data — and I mean “who” loosely, because increasingly it’s not a person. Your pipeline’s newest customer is a model making decisions at 3am. Not a VP pulling up a dashboard over coffee on Monday morning. A program, running autonomously, acting on whatever you served it.

That changes the game for data teams in ways we haven’t fully internalized yet.

Think about what it means for documentation. For data contracts. For SLAs. When a human misreads a dashboard, they Slack you a question. When an agent misreads your data, it makes a bad decision and nobody notices until the damage is done.

I’ve been consulting for data teams through this whole transition. The patterns are loud. The same problems I wrote about in 2023 — broken pipelines, ticket mills, governance gaps, teams buried in stakeholder requests — those haven’t gone away. They’re about to get amplified. Because now you’re not just serving dashboards to a dozen stakeholders. You’re serving structured context to a fleet of agents that never sleep and never ask clarifying questions.

And there’s this new term floating around: “context engineering.” I keep reading about it like it’s some brand-new discipline. Designing data systems that embed rich, machine-readable meaning alongside the data itself. And I keep thinking — didn’t we used to just call this data modeling?

The frameworks are new. The work isn’t. That’s both reassuring and a little terrifying.

What Sanity Check Is Now

Back in issue #1, I wrote about sharing recipes — not secrets. The idea was simple: you can’t share your company’s actual business insights, but you can share the patterns and approaches stripped of the secret sauce. Analysts will take those recipes and fill them with meaning for their own organization.

That premise still holds. But the kitchen is different now. The ingredients include agents, protocols, and context windows alongside SQL and YAML. The recipes need updating.

So here’s what Sanity Check is going to be:

One original take per week on data engineering and data ops — through the lens of an agentic world. Grounded in what I’m seeing in real client engagements, not what vendors are pitching at conferences. Written for data and analytics engineers who are building the systems that agents will depend on.

No “AI will replace you” panic pieces. No “just add an agent to it” magic. Practical, opinionated, and honest about what’s working and what’s not.

A sanity check. Same as always.

The Bet

Here’s what I believe: the teams that win the next two years won’t be the ones with the fanciest agent frameworks or the most bleeding-edge orchestration layers.

They’ll be the ones who got the fundamentals right. Clean models. Reliable contracts. Documentation that a machine can actually parse. And then — only then — they let agents amplify that work.

Fundamentals first. Agents second. That’s the bet this newsletter is making.

Because if your pipeline breaks every Thursday, I promise you — no agent is going to fix that.

If this resonates, you’re in the right place. Hit reply and tell me what’s keeping you up at night on your data team. I read every one.

The recipes are still worth sharing.

The kitchen just got a lot more interesting.

Welcome back to Sanity Check.

This essay anchors the relaunch of Sanity Check. The “recipes not secrets” philosophy connects to 06-reference/concepts/open-knowledge-sharing. The emphasis on craft and fundamentals over hype reflects 06-reference/concepts/analytics-as-craft. The positioning work behind this piece lives in 01-projects/newsletter/newsletter-positioning.