"The illusion of an answer is more dangerous than no answer at all."
On chat-with-data & semantic layers
A portfolio, not a résumé
Issue 01 — live, and still being written.
One line. No résumé energy. A point of view, rendered — with the receipts attached in the archive.
"The illusion of an answer is more dangerous than no answer at all."
On chat-with-data & semantic layers
"Obsessed with rigorously connecting what I'm building to business value — by working backwards from understanding the business."
Most data work asks 'is this elegant?' — Nick asks 'is this the right question?'
"I don't buy into the logical fallacies of the experts or the majority in the slightest."
Not contrarian — first-principles by default
"With another candidate, the next thing is the next thing. With me, maybe — but the thing after that is in great peril."
Forward-thinking, not just execution
"A data pipeline's time-to-value was never limited by writing joins — it's limited by understanding the business."
Where data value actually comes from
"I don't have grumpy days at the office, or days I let my standards down."
Consistency as a differentiator
"So much human capital wasted moving numbers around to make a board deck sound better — regardless of the business health underneath."
On where analytics effort goes to die
Voice · one line
"The illusion of an answer is more dangerous than no answer at all."
— Nick, on chat-with-data & semantic layers. see source
The rule it setsEvery reply from the bot cites the moment it leaned on. No interpretation without receipts.
In funnel order. Stand-alone reading; skim or commit.
In Nick's words — lightly edited for clarity. The unedited transcripts live in the archive.
I'm at heart a positive, optimistic, energetic, extroverted person who gets energy from being around people and solving problems. Hard to talk about myself without mentioning real ADHD-hyperfocus tendencies — I take a new problem and work at it until I find a solution. Serious about the mission, but myself: mixing in positive energy and awkward jokes that are often more confusing than funny.
Where I separate myself in data and analytics: I'm obsessed with rigorously connecting what I'm building to business value — by working backwards from understanding the business. A lot of smart people build elegant solutions stakeholders love; that doesn't mean they're providing real business value.
On the negative side, I tend to over-engineer — to build for the abstraction too much. Things that aren't complex to me can be overly complex to others, and I don't always predict that well. Sometimes there's a simpler path to value.
And I don't care much what the trends or "consensus" best practices are. Not overtly contrarian — but I don't buy into the logical fallacies of the experts or the majority in the slightest.
Three projects, all in active development. Each ships something real — but the real artifact is the disciplined, AI-assisted process behind it.
A local-first recurring-event tracker built to test one idea: that lists, habits, tasks, and timers are all the same primitive viewed differently. Everything is one event-sourced items row — behaviors drive logic, labels drive display. Less a finished app than an exploration of how far a few primitives stretch before complexity is forced.
A local-first desktop tool to capture work items across Azure DevOps and Jira in seconds — hotkey, voice, or paste. A half-sentence becomes a fully-fielded ticket via a Claude pipeline with per-field confidence. The deeper experiment: a governance layer around the AI agent — principles, invariants, decision records — making the codebase a proving ground for disciplined agent-driven development.
Turns Claude Code from a coding tool into a stateful project manager. One bootstrap command and 11 questions render a project skeleton: up to 19 custom slash-command skills, a versioned doc spine, and hooks enforcing consistency every turn. Not "can an AI write code?" but "can an AI run the project?"
Wireframe-level. Same components, stub content.
5–8 projects in a magazine slideshow. Headline, image, outcome.
in progress
Opinionated. The "illusion of an answer" throughline.
in progress
By theme. Citations from the chatbot link here.
POV + why-not-yet. Not a backlog.
in progress
Always in the top bar. Citations link into the archive.