Methodology · the taxonomy

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

Every agent that works a session — the lead, and any worker it dispatches — resolves to exactly one of five kinds of work, read from structure, never content. A session’s total is the sum of what each of its agents earned, so the same hours can come from new code, deletions, debugging, exploring, or coordinating a worker.

PR #2841Payments · merged
resolves to8.25expert-hours
Creation 97%Reduction 0%Repair 0%Understanding 0%Orchestration 3%
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 that survives — after the model discounts what got written, rewritten and thrown away.

97%
of this session
Reads from structure
added lines, capped at 3,000/agentcomment lines at half-creditincidental deletions at 0.3x
Example this session

The dispatched worker's new retry handler: 1,600 lines added -> 400 retained (25% retention) -> 8.00h.

How it is sized
retention x (added lines, capped + 0.5x comments + 0.3x incidental deletions) / 50 lines/hr
The currency

From agents to a number.

Each agent’s kind of work is sized into expert-hours, the session total is capped by a leverage ceiling, scaled by whether the work landed, and priced at your rate. Every step is a transparent line of working.

Expert-hours
8.25EEH

Shown with a confidence — 82% here — so the number is honest about its uncertainty, never false precision. The 5.0511.45h band sweeps the model’s two most uncertain knobs — retention and exploration pace. A leverage ceiling (1.8h active × 10) caps the total at 18h; this session is well under it.

× Outcome
1.0merged

Merge-conditioned only for the code-producing types — creation, reduction, repair: 1.0 merged, 0.85 linked but unmerged, 0.6 otherwise. This session’s own type is orchestration, which holds at 1.0 regardless — a PR isn’t the coordinator’s own deliverable.

× Your rate
$120/hr

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

= Value
$990

12.00× the $82.50 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.