Agentic profile

I'd rather let the sessions speak.

AI is a real revolution, and revolutions scramble language. Titles get recombined, and overnight self-proclaimed experts are everywhere. I'm introverted enough as it is, so rather than add to that chorus, I'd rather let my work speak for me.

What follows is how I actually work with the model, as measured by apply new, a tool built by Play New, from forty-five days of my logged Claude Code sessions. I didn't grade myself; the logs did. The unedited output is linked at the bottom.

2026-05 → 2026-06 · 41 sessions · 805 instructions · 4 products
Source: Claude Code, full capture. Log-consistency screen 100/100 (a screen, not a proof). Window and counts are lower bounds, since logs rotate and old sessions are pruned.
In one breath

A freelance designer and semiotician who also ships production code: consumer and creative apps across web and native iOS, prototypes ported into design systems, presentation decks crafted by hand. A daily driver, mostly co-thinking. Detailed briefs to launch greenfield work, then tight iterative refinement. Returns to a handful of products repeatedly: depth over breadth.

How I work with the model
directing 25%co-thinking 75%

I switch to directing mode to launch work: detailed implementation plans, thorough codebase audits, and full product briefs set the frame. Once building, I co-think, steering through short, colloquial reactions, corrections and continue-prompts rather than fresh specifications. Roughly three quarters of the exchanges.

Cognitive profile — verification-heavy · risk-calibrated

I decompose greenfield work up front through detailed plans, then track execution with structured task lists and frequent clarifying exchanges before committing to a direction. Verification is the defining habit: I inspect model output against the source, catching silently changed strings, omitted fields and prototype-to-screen divergence rather than accepting work at face value. Risk is calibrated by context: I let the model push freely on personal projects, and stay tight and low-churn on client deliverables (zero reverts).

Practice intensity — daily driver
Active days30 / 45 · 67%
Longest streak13 days
Median sessions / active day2
Median session depth43 tool calls
Peak day1,058 tool calls
Agentic literacy

A mature stack, used as standard tooling rather than novelty:

Where the work goes
Trajectory

Over the window the practice shifted from exploration toward confident execution. Prompts grew more specified and delegation roughly doubled, while the ratio of research to actual changes fell: less circling, more building. Verification rose in step, so faster execution did not cost scrutiny.

median prompt words  11 → 15
research : mutation  0.75 → 0.60
verification rate  22% → 26%
On trusting this
Groundedness — claims supported by logs27 / 27
Log-consistency screen100 / 100

These are screens, not proofs. The honest move is to read the raw data and judge for yourself.

Raw data

The unedited output of the tool, exactly as generated. The page above is just the readable rendering.