Workflow — how the Talomnia Workforce market research was produced

The case in two minutes #

What the client asked

The production trail of the market research: two parallel researcher lanes (competitors/ICP and price benchmarks), a primary self-use measurement from the Workflow Ledger, document assembly with fact-checking — and, as a separate act, publication through a Knowledge Contract after the R1 customer review (issue #42, R1-03 and R1-14). The research findings live on the Research page; this page carries only the process: steps, roles, time, cost, evidence.

Who executed

10 execution entries · 3 roles · 5 agent sessions

Capabilities

created: 20 · reused: 12 · modified: 6

Checks

validated: 10 · rejected: 0 · reworks: 0

Result

From framing to the finished document the research took 20 minutes 11 seconds of wall time and cost ≈ $8.43 in model spend (token-based estimate, basis recorded in the ledger) — five accounted execution units of a single researcher role. The gap between production and publication is this case's main lesson: finished work that never projects onto the public surface does not exist for the client (the R1 review recorded that as a blocking finding, and the R2 review as "written and withheld"). The publication is accounted as its own steps under its own contract.

Acceptance status

done

Coverage and currency

10 execution entries · snapshot 2315ae988fd2

The entry count and digest state which set the totals were computed from. The digest is taken over EVERY figure in this block rather than over selected columns, so it changes when membership changes or when any figure beside it changes. An attestation narrower than its apparent scope is worse than none, because it buys trust it has not earned.

Every figure above is derived from the execution ledger and the artifact matrix below. The conclusions text is written by hand and is pinned to the entry count: if the ledger moves past it, the projection refuses to load rather than publish a stale claim.

Failures and rework #

Derived directly from this case's execution ledger: no failed or reworked unit is hidden. Zero is a statement too.

Failed: 0 · Reworked: 0 · 10 of accounted units

Case economics #

Where the money and the time went #

Between one grand total and a ledger of hundreds of rows sits the breakdown: by role, by stage and — the one that matters — how much bought KNOWLEDGE versus how much was EXECUTION on knowledge that already existed. Every bar carries its own confidence marker: measured and reconstructed figures are never added into one number.

Confidence of these sums

Not one ledger row in this case is measured telemetry: the measured share is 0%. Every sum below is reconstructed after the fact from token counters and rates, with the basis of each estimate recorded in the ledger row itself. That is precisely why we publish the breakdown: a figure that does not say where it came from is not evidence.

By role

By stage

A stage’s money comes from the ledger entries of the tasks that stage declares it covers, not from the caption under the timeline step. Stages sharing the same task set are merged into one bar: the ledger does not resolve finer than the task there, and splitting it further would be an invented allocation.

Producing knowledge versus executing on it

Classification rule: an execution unit counts as "producing knowledge" when at least one artifact it created or modified resolves to a Capability Atlas entity — by the same match the artifact matrix below uses. A unit that both produced knowledge and delivered work counts wholly as knowledge production. That is deliberately conservative: the rule can only inflate the knowledge side, so the published knowledge cost is an upper bound and the reuse claim is never flattered by it.

Created and reused

Knowledge elements engaged

15

Uses of them by execution units

35

Average units per element

2.33×

Elements used by more than one unit

6

Knowledge-artifact touches (created / modified / reused)

0 / 0 / 1

Delivery-artifact touches (created / modified / reused)

20 / 6 / 11

Two different quantities, and not interchangeable: "touches" count what a unit did to an artifact, "uses" count how many units executed on that knowledge element. The reuse claim rests on the second.

Timeline caption reconciled against the ledger

The timeline step captions reconcile with the ledger entries: no divergence.

Stage timeline #

1. 2026-08-19

   context-intake

   researcher — research brief and decision questions (rates context, consultation pricing, first sellable service) · public repository · 6m / $2.26

2. 2026-08-19

   desk-research-pricing-benchmarks

   researcher — price benchmarks across thirteen adjacent categories, per-figure source grades · public repository · 5m / $1.85

3. 2026-08-19

   desk-research-competitors-icp

   researcher — competitive landscape, failure modes of the category, ICP inputs · public repository · 8m / $1.96

4. 2026-08-19

   document-authoring-and-factcheck

   researcher — the ten-section research document with inline source grades and the self-use unit-economics measurement · public repository · 13m / $2.03

5. 2026-08-19

   reporting-and-ledger

   researcher — lane report and Workflow Ledger entries · public repository · 1m / $0.33

6. 2026-08-19

   source-verification-for-publication

   researcher — source-verification manifest — every published citation fetched, outcomes and discrepancies recorded · public repository · 17m / $1.11

7. 2026-08-19

   publication-under-contract

   knowledge-curator — Research page with the full R1-03 section set, reciprocal Workflow link, projection to the site database · public repository · 23m / $3.38

Conclusions #

From framing to the finished document the research took 20 minutes 11 seconds of wall time and cost ≈ $8.43 in model spend (token-based estimate, basis recorded in the ledger) — five accounted execution units of a single researcher role. The gap between production and publication is this case's main lesson: finished work that never projects onto the public surface does not exist for the client (the R1 review recorded that as a blocking finding, and the R2 review as "written and withheld"). The publication is accounted as its own steps under its own contract.

Research #