gpt-oss-120b on “A memo on composing costs”: better with Minto on both measures

Structure 4 → 5 of 8 +1 Quality 4 → 7 of 10 +3

The judge on the output with Minto

It is the only output to state the reader’s question literally, but it retains benchmarking as an action and omits the staffing branch.

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

Structure of 8, 2 points per axis
Structure	Without Minto 4	With Minto 5	Change
Top	2	2
Key-line composition	1	1
Levels	0	0
Order and kind	1	2	+1

Quality of 10, 2 points per axis
Quality	Without Minto 4	With Minto 7	Change
Top	2	2
Same-kind grouping	0	2	+2
Explainable order	1	2	+1
MECE	0	0
Visible, proportionate structure	1	1

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

Without Minto With Minto

Without Minto

control prompt · blind label out-11

invented_facts
unacknowledged_source_loss

Extensive invented estimates, timing, owners, automation examples, and rollout mechanics overwhelm a mixed first level and still miss the wage action.

To: Engagement Manager – TTW Project
From: Junior Consultant – Composing‑Room Review
Subject: Action‑Oriented Recommendation to Reduce TTW Composing Costs

Recommendation

Pilot a simplified composition process for low‑complexity titles and test targeted productivity‑enhancing changes.
If the pilot confirms the expected 10 %‑15 % reduction in composing cost, roll the changes out across the department to achieve a total cost saving of roughly 5 %–7 % of overall hard‑back and paperback production costs.

Supporting Arguments

Composition dominates production cost and TTW lags the industry.
- Composition accounts for ~40 % of hard‑back and 50‑55 % of paperback cost.
- Benchmark data show TTW’s measured productivity is 20 %–50 % below comparable printers, indicating excess cost rather than a pricing issue.
A focused simplification can deliver measurable savings.
- Reducing or re‑timing quality‑control checks on inexpensive titles is projected to cut composing cost by up to 10 % for those titles.
- Changing the composing method (e.g., increasing automation, revising workflow) has the potential to close the 20 %–50 % productivity gap.
The department’s capacity constraints make a pilot essential.
- Manual composition is already overloaded; overtime exceeds budget by >50 %.
- Recent staff turnover (two compositors lost) and difficulty hiring at below‑market rates limit the ability to implement broad changes without first proving impact.
A structured pilot provides the evidence needed for a full rollout.
- Select a representative sample of low‑complexity titles (e.g., novels, short non‑technical works).
- Measure cost, cycle‑time, and quality before and after removing/re‑sequencing specific checks.
- Use the results to quantify savings, assess quality impact, and refine the new workflow before scaling.

Implementation Plan (Next 6‑8 weeks)

Phase	Action	Owner	Deliverable
1. Design	Define pilot scope, select titles, map current checks	Consultant + Production Lead	Pilot charter (Week 1)
2. Baseline	Capture current cost, cycle‑time, defect rates for selected titles	Production Team	Baseline data set (Week 2)
3. Intervention	Remove/re‑time identified checks; trial alternative composing method	Production Team	Adjusted workflow (Weeks 3‑4)
4. Measurement	Compare post‑intervention metrics to baseline	Analyst	Pilot results report (Week 6)
5. Decision	Evaluate savings, quality impact, and scalability	Management	Go/No‑Go decision (Week 7)
6. Roll‑out Planning	Develop department‑wide implementation plan if pilot succeeds	Consultant + Ops	Full‑scale rollout plan (Week 8)

What Was Omitted

Names of interviewees (Roy Walter, Brian Thompson, George Kennedy) – not required for decision making.
Detailed discussion of union claim – noted only insofar as it underscores the need for a controlled pilot.
General statement that managers disagree about cost levels – the analysis shows costs are indeed excessive; consensus on investigation is implicit in the recommendation.
Suggestion to compare with three other printers – benchmark data already provide the necessary context; additional comparative case studies would not change the immediate action.
Broad statements about “weak productivity” without quantification – replaced with specific benchmark gaps (20 %–50 %).

With Minto

prompt with the skill · blind label out-02

unacknowledged_source_loss

It is the only output to state the reader’s question literally, but it retains benchmarking as an action and omits the staffing branch.

Situation – Composition is TTW’s largest production cost (≈ 40 % of hard‑back and 50‑55 % of paperback), and TTW is uncompetitive on simple titles.
Complication – Benchmarks show TTW’s composing productivity 20‑50 % below peers; overtime exceeds budget by > 50 % and staffing shortages limit capacity.
Question – How can TTW lower its composing costs?

Answer – TTW should pilot a simplified composition process for inexpensive titles and launch a methods study to improve productivity, targeting up to a 10 % reduction in composing costs.

Key actions

Pilot test a simplified process
- Choose a representative sample of inexpensive titles.
- Reduce or re‑time quality‑control checks.
- Measure impact on quality, customer satisfaction, and cost.
- Expected saving: up to 10 % of composing cost.
Methods study for productivity gains
- Map the current manual composition workflow.
- Identify bottlenecks and low‑productivity steps.
- Benchmark against industry best practices (20‑50 % productivity gap).
- Develop recommendations for tool or process changes.
Benchmarking for context
- Compare TTW’s composing cost structure with three peer printers.
- Use findings to validate cost‑reduction targets.
- Note: a simple cost comparison alone will not resolve all issues.

Omitted material – Detailed staffing shortages, overtime budget overrun, union claim, narrative of department overload, and the statement that managers disagree about cost levels (these do not directly support the recommended actions).

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	absent
Unsupported certainty, causal claims, or implementation details are introducedthe skill has the rule; the model did not follow it · Mode 3, “Invent nothing”	present	absent
Omitted source material is not fully acknowledgedthe skill has the rule; the model did not follow it · Mode 3, preservation and dropped-fact rule	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 0
with Minto 3
Are benchmark, process, staffing, delay, and overtime observations below the actions?
without No; observations are promoted as first-level arguments
with Minto No; staffing is omitted
Was irrelevant comparison/opinion material omitted with an explicit note?
without Yes
with Minto No
Is the reader's question stated literally?
without No
with Minto Yes

Judge’s check	without	with Minto
Answer first	yes	no
First-level elements	4	3
First-level kind matches the gold	no	yes
Invented facts	yes	no
Source lost without a note	yes	yes
Mode respected	yes	yes
Reader’s question stated literally	no	yes
Order type named	no	no
SCQ introduction present	no	yes

How the test was built

gpt-oss-120b 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 · skill from commit f4813ce · run v1.7.0-final