How I work · AI-assisted systems · clear ownership

I use AI to move faster without outsourcing the important decisions.

A working method for framing decisions, testing assumptions, and making ownership visible.

I start with the decision, not the tool. I map the system around it, expose assumptions that could break it, test the result, and adapt the scope when reality disagrees. AI handles repeatable implementation; I decide what evidence is enough and what is ready to release.

The boundary I set the rules, check the evidence, and own the release decision. AI helps me build faster, but I decide what the system is for, what evidence counts, what it is allowed to touch, and when the result is ready to release.
6 projects using the same operating loop
11 Options incidents tracked internally
5 receipt-backed case studies with inspectable sources
2 promising Sports ideas overturned by follow-up checks
What I own

Translate the business question before touching the tool.

A request such as “find the best campaigns” or “automate the search” sounds clear until someone has to decide what “best” or “automate” means. I start there, before touching a tool.

01 / Decision What decision is this for? A report is useful only if a team can do something different because of it.
02 / Failure modes What could make the answer misleading? Late information, missing records, repeated testing, and a convenient definition are common failure points.
03 / Boundary What must I decide? Software can collect, compare, and flag. I decide what it may touch, what evidence is enough, and when a result is ready to release.
Where the method lives

The reusable six-question loop has its own page.

This page stays about judgment: how I frame the work, where AI fits, and what I own. How I check the work carries the shared questions, controls, incidents, and readiness stages.

The practical point The goal is not to make every answer look confident. The goal is to make confidence proportional to what was actually checked.
Foundational principles

Think strategically. Build systemically. Test the story. Adapt on evidence.

These are not abstract values added after the work. They are the habits that show up across the portfolio, whether the output is a marketing measurement system, a paper-trading testing process, a game, or a content pipeline.

01 / Strategy Strategic thinking Start with the decision, audience, constraint, and next action. The marketing measurement study asks what should change now; Delve starts with the habit the game should create; the YouTube video workflow starts with what a viewer would want to keep watching.
02 / Systems Systems thinking Map the full loop: inputs, rules, transformations, decisions, feedback, and failure modes. A dashboard, game loop, or publishing queue is only useful when the handoffs make sense together.
03 / Rigor Rigorous testing Test the hardest examples, keep some data aside, record failures, and repeat the important checks. If the evidence cannot survive a skeptical question, the headline is not ready.
04 / Adaptability Adaptability Change the scope when reality changes. Keep the source of truth, separate implemented work from exploration, and make uncertainty visible instead of protecting an old plan.
The thread across projects I move quickly, but I do not want speed to erase context. The system should become easier to inspect as it grows, and the next decision should become clearer, not merely more automated.
Where AI fits

AI helps me build faster. It does not decide what is true.

I am open about being heavily AI-assisted in implementation. That makes the review discipline more important, not less. A fast wrong answer is still wrong, and a polished interface can make a weak assumption harder to notice.

I own the question. I decide what the work is for and which claims are worth publishing.

I own the boundary. I decide what the system may collect, change, send, spend, or publish.

I own the checks. I ask for tests, hostile examples, fresh-source checks, and a readable record of what happened.

I own the final explanation. If a reader needs a glossary to understand the headline, the headline is not finished.

One real example, not a principle

What owning the final explanation looked like when the prediction was wrong.

In the marketing measurement study, I wrote down a prediction before the analysis ran: one week of data would not be reliable enough to agree with the final answer. That was the rule before the result existed.

The result said the opposite. One week agreed with the final answer most of the time, but not always. I kept the original prediction, labeled it partly contradicted, and kept it in the record rather than quietly rewriting or removing it. The result is shown here while the source project remains private. See the measured result and method →

Why this matters more than a principle Anyone can say they welcome evidence. The habit becomes real when the evidence contradicts your own earlier guess and the guess stays visible.
Boundaries

Automation should make attention cheaper, not judgment disappear.

Every project on this site has a line it will not cross without me. Four examples, in the words that actually apply.

01 / Money Money The options system can research and paper-test. A standing rule still keeps it away from real-money trading.
02 / Search criteria Search criteria Shortlist scores against a profile I write and revise by hand. It never redefines what counts as a good match without me changing that file first.
03 / Publishing Publishing The YouTube video workflow can narrow a large queue and assemble a draft. I review and approve anything that ships.
04 / Marketing Marketing decisions The marketing measurement study can expose a timing problem. It does not replace the team deciding how to allocate the budget.
If this sounds like how you'd want to work

A good fit? Let’s talk.

These are the habits I bring to every project on this site, not just the ones with a public write-up.