Claude Sonnet 5 on “A memo on composing costs”: with Minto, worse on structure, quality unchanged

Structure 6 → 5 of 8 −1 Quality 7 → 7 of 10 0

The judge on the output with Minto

The answer follows a contextual opening, while the memo incorrectly separates staffing from composing-cost reduction.

Mode write · case 02-ttv · run v1.7.0-final

Structure of 8, 2 points per axis
Structure	Without Minto 6	With Minto 5	Change
Top	2	2
Key-line composition	1	1
Levels	1	0	−1
Order and kind	2	2

Quality of 10, 2 points per axis
Quality	Without Minto 7	With Minto 7
Top	2	2
Same-kind grouping	2	2
Explainable order	1	1
MECE	0	0
Visible, proportionate structure	2	2

Outputs and the judge’s words are quoted as written, in English.

Without Minto With Minto

Without Minto

control prompt · blind label out-08

invented_facts

Useful staffing facts survive only as context explicitly denied the status of a solution, while “at least 10%” reverses the source’s upper-bound estimate.

To: [Aylesbury management]
From: [Consultant]
Subject: Reducing TTW's composing costs

We recommend TTW pursue two actions to reduce composing costs, which we estimate could save at least 10% of total composing cost, with more potentially available from a productivity study.

Simplify the quality-control process for simple titles. Every title—complex reference book or simple novel—currently passes through the same checking stages. We recommend testing fewer or differently timed checks on selected jobs and measuring the effect on quality and customer satisfaction. Estimated saving: 10% of total composing cost.
Investigate productivity through a formal methods study. TTW's measured productivity trails the industry benchmark by 20-50%. George Kennedy has agreed to test which stages can be removed and why productivity lags. This study should identify the specific causes and quantify further savings.

Supporting context

Composition is TTW's largest production cost (roughly 40% of hardback cost, 50-55% of paperback), and industry comparisons show TTW is uncompetitive, particularly on simple work. The department is also under capacity pressure: manual composition is short-staffed, pay is below local market rates, two compositors have recently left, most jobs are running late, and overtime is over 50% over budget. These pressures make the recommended actions more urgent but are not themselves solutions—they explain why action is needed now.

Omitted or demoted from the original note:

The list of people interviewed (Roy Walter, Brian Thompson, George Kennedy) is omitted as procedural detail not relevant to the recommendation, except Kennedy's role, which is retained because he owns the productivity study.
The suggestion to compare costs with three other printers is omitted; the note itself judged this unlikely to settle the issue.
The observation that managers disagree about whether costs are high is omitted, since all agreed to investigate and the disagreement does not affect the recommended actions.
The union claim is omitted as a separate issue not tied to the composing-cost question.

With Minto

prompt with the skill · blind label out-13

invented_facts

The answer follows a contextual opening, while the memo incorrectly separates staffing from composing-cost reduction.

To: [Engagement Manager]
From: [Consultant]
Subject: TTW composing costs — recommended next steps

Composition drives 40% of hardback and 50-55% of paperback cost, and TTW is uncompetitive on simple work — but we still don't know whether that cost is actually excessive, because every title, simple or complex, runs through the same quality-control stages regardless of need. Two weeks of fact-finding point to a clear next step: run two parallel tests to find out where the money can come out — simplifying quality control on simple titles, and improving compositor productivity.

Test whether quality control can be simplified on simple titles
- Select a sample of straightforward jobs and reduce or retime the checks they go through
- Measure the effect on quality and customer acceptance before rolling out
- Potential saving: up to 10% of total composing cost
Test whether a different composing method raises productivity
- Commission a methods study on manual composition, the tightest capacity constraint
- TTW currently trails the productivity benchmark by 20-50%; the study should identify where that gap can close
- George Kennedy has agreed to run this test

What I need now: sign-off to launch both tests, with Kennedy leading the productivity study.

Dropped from the source and not carried above, because none of it supports the recommendation directly:

The list of people interviewed (Roy Walter, Brian Thompson, George Kennedy) beyond naming who will run the test.
Staffing detail (below-market pay, two recent departures, late jobs, overtime 50%+ over budget, union claim) — real problems, but a separate issue from composing-cost reduction; worth its own note if you want it addressed.
The suggestion to compare costs against three other printers — I don't think a simple comparison would settle the question, so I left it out rather than list it as a third workstream.
The observation that managers disagree on whether costs are high — moot once the tests produce data.

The judge

Recurring defect	without	with Minto
Process simplification and method/productivity change remain duplicate branchesthe skill has the rule; the model did not follow it · Core loop §6, MECE duplication test	present	present
The wage action remains buried in observations or disappearsthe skill has the rule; the model did not follow it · Core loop §§4 and 6, promotion of the real branch from observations	present	present
Staffing evidence is placed in context, attached to the methods branch, or omittedthe rule is there but buried · Core loop, vertical support and levels	present	present
The literal reader question is absentthe skill has the rule; the model did not follow it · Core loop §§1 and 3	present	present
Unsupported certainty, causal claims, or implementation details are introducedthe skill has the rule; the model did not follow it · Mode 3, “Invent nothing”	present	present
No output names one of the prescribed order typesthe rule is there but buried · Core loop §5, obscured by Mode 3’s clean-text guidance	present	present

Decisive questions

Were process simplification and method/productivity change merged as one branch?
without No
with Minto No
Was raising wages promoted to the first level?
without No
with Minto No
How many first-level elements are actions?
without 2
with Minto 2
Are benchmark, process, staffing, delay, and overtime observations below the actions?
without Yes, as undifferentiated supporting context
with Minto No; the staffing chain is omitted
Was irrelevant comparison/opinion material omitted with an explicit note?
without Yes
with Minto Yes
Is the reader's question stated literally?
without No
with Minto No

Judge’s check	without	with Minto
Answer first	yes	no
First-level elements	2	2
First-level kind matches the gold	yes	yes
Invented facts	yes	yes
Source lost without a note	no	no
Mode respected	yes	yes
Reader’s question stated literally	no	no
Order type named	no	no
SCQ introduction present	no	yes

How the test was built

Claude Sonnet 5 received the same task twice. The control prompt is one framing line and the task. The prompt with Minto is the same task preceded by the full text of the skill. The judge read both outputs among 14 under blind labels and did not know which one had the skill.

Prompt without Minto 2 516 B

You are working on a business document using the Minto Pyramid Principle.

<!-- Faithful paraphrase of Minto (2010), Chapter 3, the TTW composing-room
     memorandum before restructuring. Original wording for this fixture. -->

# Fixture 02: TTW composing costs

**Mode:** `write`
**Language:** `en`

## Context

TTW is a printing company in Aylesbury. A junior consultant spent two weeks
examining composing-room costs. The engagement manager already knows that
composition accounts for roughly 40% of hardback cost and 50-55% of paperback
cost, that TTW is uncompetitive on simple work, and that TTW does not know
whether its composing costs are actually excessive.

## Before

```text
To:
From:
Subject: TTW

This note records the information gathered during the past two weeks.

Composition is the largest production cost. Industry comparisons suggest weak
productivity and high cost at TTW. Every title, whether a complex reference
book or a simple novel, passes through essentially the same quality-control
stages.

People in Aylesbury want to understand the causes. I spoke with Roy Walter,
Brian Thompson, and George Kennedy. Kennedy is willing to test whether some
stages can be removed and why measured productivity trails the benchmark.

The department is overloaded. Manual composition is especially short of
capacity. TTW pays below local market rates, struggles to hire and retain
compositors, has just lost two employees, and now runs most jobs late.
Overtime is more than 50% over budget, while the union is pressing a new claim.

Conclusions

1. Costs may be reduced by:
   a. simplifying the process for inexpensive titles;
   b. increasing productivity by changing the composing method.

2. To simplify the process, TTW should test selected jobs and measure the
   effect of fewer or differently timed checks on quality and customers. The
   saving might reach 10% of total composing cost. A separate methods study
   could identify further productivity improvements because TTW trails the
   benchmark by 20-50%.

3. Comparisons with three other printers might provide useful context, although
   I doubt a simple comparison will settle the issue.

4. Managers disagree about whether costs are high, but all are willing to
   investigate.
```

## Task

Rewrite the report using the Minto Pyramid Principle. Keep the useful facts,
remove or demote material that does not support the recommendation, and state
what was omitted.

Return only the result, with no explanation of how you produced it.

Prompt with Minto five parts, in order · 30 089 B

Below is a skill written as an instruction. Read it in full and apply it to the task at the end.
===== SKILL.md ===== SKILL.md at f4813ce 17 235 B
===== references/rules.md ===== references/rules.md at f4813ce 6 464 B
===== references/templates.md ===== references/templates.md at f4813ce 3 742 B
===== TASK ===== the whole case input
Return only the result, with no explanation of how you produced it.

Case input before.md

Fixture 02: TTW composing costs

Mode: write
Language: en

Context

TTW is a printing company in Aylesbury. A junior consultant spent two weeks
examining composing-room costs. The engagement manager already knows that
composition accounts for roughly 40% of hardback cost and 50-55% of paperback
cost, that TTW is uncompetitive on simple work, and that TTW does not know
whether its composing costs are actually excessive.

Before

To:
                From:
                Subject: TTW
                
                This note records the information gathered during the past two weeks.
                
                Composition is the largest production cost. Industry comparisons suggest weak
                productivity and high cost at TTW. Every title, whether a complex reference
                book or a simple novel, passes through essentially the same quality-control
                stages.
                
                People in Aylesbury want to understand the causes. I spoke with Roy Walter,
                Brian Thompson, and George Kennedy. Kennedy is willing to test whether some
                stages can be removed and why measured productivity trails the benchmark.
                
                The department is overloaded. Manual composition is especially short of
                capacity. TTW pays below local market rates, struggles to hire and retain
                compositors, has just lost two employees, and now runs most jobs late.
                Overtime is more than 50% over budget, while the union is pressing a new claim.
                
                Conclusions
                
                1. Costs may be reduced by:
                   a. simplifying the process for inexpensive titles;
                   b. increasing productivity by changing the composing method.
                
                2. To simplify the process, TTW should test selected jobs and measure the
                   effect of fewer or differently timed checks on quality and customers. The
                   saving might reach 10% of total composing cost. A separate methods study
                   could identify further productivity improvements because TTW trails the
                   benchmark by 20-50%.
                
                3. Comparisons with three other printers might provide useful context, although
                   I doubt a simple comparison will settle the issue.
                
                4. Managers disagree about whether costs are high, but all are willing to
                   investigate.

Task

Rewrite the report using the Minto Pyramid Principle. Keep the useful facts,
remove or demote material that does not support the recommendation, and state
what was omitted.

The judge’s gold gold.md

Gold 02: TTW composing costs

Source structure: Minto (2010), Chapter 3, TTW analysis and rewritten memo.

Expected structure

Element	Expected value
Reader question	How can TTW reduce composing cost?
Top	TTW can reduce composing cost substantially
Key-line kind	Actions
Order	Two independent changes, each followed by its causal support

Key line

Eliminate unnecessary stages from the composing process for simple work.
Raise wages to competitive levels.

The source's "simplify the process" and "increase productivity by changing the
method" are overlapping descriptions of the same process intervention. They
must not survive as two separate first-level branches. The missing second
branch is embedded in the observations: low wages cause vacancies, delays, and
overtime cost.

Levels

Under eliminating stages: every job follows the same process; TTW trails the
benchmark by 20-50%; run a controlled experiment; potential saving up to 10%.

Under raising wages: below-market pay; hiring and retention difficulty; two
departures; understaffing; late work; overtime more than 50% over budget; union
pressure.

Names, conflicting opinions, and generic competitor comparisons do not answer
the reader's question. They may be omitted with one explicit note.

Judge gpt-5.6-sol, effort high · Claude Sonnet 5, effort low · skill from commit f4813ce · run v1.7.0-final