Methodology · the taxonomy

We don’t count lines.
We measure expert-hours.

Every session resolves to a mix of five kinds of work — read from its structure, never its content. Each kind is sized by its own transparent formula, so the same hours can come from new code, deletions, debugging, or coordinating subagents.

PR #2841Payments · merged
resolves to3.2expert-hours
Creation 48%Reduction 7%Repair 22%Understanding 14%Orchestration 9%
The five kinds

Five kinds of work.

Pick one. The same expert-hours can come from any of them — each read from structure, each sized its own way.

Kind 01 of 5

Creation

Net-new capability — structure and behavior that did not exist before.

48%
of this session
Reads from structure
+ added linesnew filesnew symbols
Example this session

A new retry handler, wired up with its tests.

How it is sized
net-new structure → hours, via the creation curve
The currency

From a mix to a number.

The mix is sized into expert-hours, scaled by whether the work landed, and priced at your rate. Every step is a transparent line of working.

Expert-hours
3.2EEH

Shown with a confidence — 78% here — so the number is honest about its uncertainty, never false precision.

× Outcome
1.0merged

Did the work land? Shipped scores high; abandoned is discounted. Range 0.6 – 1.3.

× Your rate
$120/hr

The one number you set. It never leaves your workspace.

= Value
$384

2.08× the $184.20 of AI spend — expert work returned per dollar.

Why expert-hours

A line count
is not value.

Diff size rewards verbosity and treats every change as equal. Expert-hours measure the work, not the output.

Counting lines

Verbosity wins — more lines reads as more work, even when the result is worse.

Churn and copy-paste inflate the count without adding any value.

Deletions and refactors look like nothing, yet are often the hardest work.

It assumes a speed-up the evidence does not support.

Expert-hours instead

Sized by outcome — the hours the work would have taken an engineer.

Deletions, debugging and orchestration each carry their own hours.

Content-free and deterministic — identical inputs, identical figure.

Always a number with a confidence — honest about its uncertainty, never a false point.

Under the hood

We’d love your feedback.

Each kind is sized by its own transparent formula over structural signal — line counts, tokens, turns, tool calls, subagents — never the content of your code.

We attach a confidence to every number, not false precision — and we tighten it as we reconcile estimates against real outcomes. Every figure is an inspectable line of working, never a black box. If a number looks wrong for your team, tell us; that feedback sharpens the model.

Check our working

The research we lean on.

Nothing unexplainable at renewal

Run the pipeline on
your own work.

Connect a repo and step through the real pipeline behind every figure — stage by stage, inputs to dollars.