Skip to content

Practice — Data

Get the data right first. Everything interesting comes after that.

  • BigQuery
  • Postgres
  • GA4
  • Semantic layer
  • AI SDK
  • Agents
  • Evaluation

Most analytics problems are not analytics problems. The numbers exist, but they live in five tools, two of them disagree, nobody trusts the third, and the person who needs the answer cannot write the query. No interface fixes that — the layer underneath has to be boring, typed and reproducible first.

This page is where I keep the data side of my practice: how I build foundations, and where I think this is heading. It is a working position, not a pitch.

Layer
Ingestion, modeling, semantics, access, evaluation
Tools
Postgres, BigQuery, GA4, dbt-style modeling, TypeScript
Applies to
Creators with an audience, small and mid-size companies
Stage
Building in public — no product, no waitlist, yet

The order of operations

There is a tempting shortcut in every data project: build the interface, wire it to whatever tables exist, demo it. It works for exactly one demo, on one dataset, with the person who built it holding the mouse. The order below is slower and holds up.

  1. 01Ingest. Boring connectors, idempotent loads, replayable history.
  2. 02Model. Explicit grain, explicit keys, explicit definitions.
  3. 03Name the metrics once, in a typed layer that humans and models both read.
  4. 04Only then put conversational access on top.
  5. 05Only then let agents act — and score every action against outcomes.

Why conversational access matters

The bottleneck in most teams is not the dashboard, it is the translation step: someone has a question in business language and someone else has to turn it into a query. Removing that step changes who is allowed to be curious. But it only works if questions resolve against a semantic layer instead of raw tables — otherwise you have built a machine for producing confident mistakes.

Evaluated agentically

Once agents act on data, "does it feel right" stops being an acceptable answer. I treat an agent run like a landing page variant: define the outcome, record the whole run, score it on three axes, keep what wins.

  1. 01Correctness — did it resolve against the semantic layer, or invent a column?
  2. 02Cost — tokens, latency, tool calls. A right answer in ten seconds is a different product than in one.
  3. 03Consequence — did the action move the metric it claimed it would?

Who this is for

The same foundation serves a creator with one audience and a mid-size company with fifty accounts. Different scale, identical questions: what is working, what is it worth, what should happen next. That overlap is the part I find genuinely interesting.

Selected work

  • building2026 — ongoing

    Data foundation & agentic evaluation

    An ongoing build: modeled data, a typed metric layer, conversational access, and agent runs scored against recorded outcomes.

    • Next.js
    • TypeScript
    • Postgres
    • BigQuery
    Case study

Writing

  • 5 min

    Data first, product second

    Why I refuse to build the chat interface before the data layer is boring, typed and trustworthy.

    • data
    • product
    • ai
    Read note

Data that should be easier to ask questions of?

I am always up for comparing notes on modeling, semantic layers and agent evaluation — whether or not there is a project attached.