Code
Where information meets attention
Every decision rests on information. The constraint is the time and resources needed to gather it, understand it and decide what it means.
So we compromise. We do enough to reach a decision that is good enough.
Machines, software and now LLMs allow us to reconsider where that threshold sits. Which parts of the work still need human attention? Which can a system handle reliably?
The point is not to reduce operational staffing costs. It is to ask what human attention can do once it is no longer absorbed by work that used to require it. That creates room for a service or product to evolve towards a new expectation, set by human imagination rather than the limits of the old process.
Laravel · Vue · Python · FastAPI · React · Next.js · PostgreSQL · REST APIs
Working pilots
Assessment Desk
A partial demo of criterion-bound AI feedback, built so a teacher can check each judgement against the student’s work and disagree.
Impact Desk
A demo of nonprofit records kept against the questions a funding review will ask, on fictional data.
Production Desk
A work-in-progress demo of pricing a live show across departments, from the supplier’s side.
Ingest Lens
A working intake layer that turns fragmented documents into reviewable records inside the operational hubs where human attention is needed.
Practice Engine
A deliberate-practice prototype for turning structured source material into focused, reviewable drills.
Image Prompt Studio
A library for the characters, poses, settings and wording that worked, so human direction stays consistent across images.
Experiments
Music Analyzer
Interpretable score analysis, natural-language retrieval, and exact playback from real orchestral recordings.
Dome Stage
An interactive fulldome theatre built in the browser, where music, light and dome imagery share one scene.
Crowded Mind
An identity-led website that turns the moment before an idea chooses its medium into an interactive editorial experience.