qwen3.6-35b-a3b on “A message about technical debt”: worse with Minto on both measures

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

The judge on the output with Minto

The three reasons are visible, but the order runs backward and user-post evidence is attached to churn.

Mode write · case 08-techdebt · run v1.7.0-final

Structure of 8, 2 points per axis
Structure	Without Minto 7	With Minto 6	Change
Top	2	2
Key-line composition	2	2
Levels	1	1
Order and kind	2	1	−1

Quality of 10, 2 points per axis
Quality	Without Minto 8	With Minto 7	Change
Top	2	2
Same-kind grouping	2	2
Explainable order	2	1	−1
MECE	1	1
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-04

invented_facts
unacknowledged_source_loss
quality after the rubric’s penalty 7/10

It closely follows the gold hierarchy, though formal presentation and strengthened causal claims make it less disciplined.

Subject: Recommendation: Dedicate Next Sprint to Reducing Defect Backlog

Hi Alex,

I recommend using the next sprint to reduce the defect backlog. This intervention is necessary to address an unsustainable technical trajectory and mitigate immediate risks to retention and revenue.

1. Backlog growth outpaces resolution
Incoming defects now exceed our closure rate. The attached projection indicates the backlog will expand significantly over the next year without dedicated remediation time.

2. Defects are driving churn
Customer experience data shows a direct correlation between defect volume and churn. Recent interviews reinforce that stability issues are causing customers to leave.

3. Revenue and brand impact are accelerating

Sales: Close rates are falling as prospects cite reliability concerns.
Major Account: We received a formal complaint from a key client regarding these issues.
Sentiment: Public user posts reflect growing dissatisfaction.

Please let me know if you approve this focus for the upcoming sprint.

Best,

[Your Name]

With Minto

prompt with the skill · blind label out-12

invented_facts
unacknowledged_source_loss
quality after the rubric’s penalty 6/10

The three reasons are visible, but the order runs backward and user-post evidence is attached to churn.

Subject: Recommendation: Dedicate next sprint to reducing defect backlog

As we plan the next sprint, our incoming defect rate exceeds our fix rate, projecting a widening backlog that is actively harming retention and revenue. Customer data links this backlog directly to increased churn, while a major account complaint and falling sales close rates signal immediate pipeline damage. To arrest this trend, we must dedicate the next sprint to reducing the defect backlog.

Why this is critical:

The backlog is driving churn. Churn correlates with defect volume, reinforced by user posts and interview feedback showing severe customer frustration.
The backlog is eroding sales velocity. A major account has lodged a formal complaint, and Sales reports falling close rates attributed to these quality concerns.
The backlog is accelerating. Incoming defects consistently outpace fixes, projecting a worsening trajectory that compounds the risk daily.

Decision needed: Approve the next sprint focus as defect reduction.

The judge

Recurring defect	without	with Minto
Evidence omitted or conflated instead of retained beneath a parentthe skill has the rule; the model did not follow it · Mode 3 — “Keep every fact from the source”	present	present
Unsupported precision, causal strengthening, or new forecaststhe skill has the rule; the model did not follow it · Mode 3 — “Invent nothing”	present	present
Situation and complication absent before supportthe skill has no such rule · Core loop §3 — SCQ intro	present	absent
Sequence of reasons lacks a useful explanatory progressionthe rule is too vague to follow · Core loop §5 — Order	absent	present
SCQ labels and memo apparatus are disproportionate for a colleague messagethe skill has the rule; the model did not follow it · Mode 3 — clean text and implied format	present	present

Decisive questions

Recommendation
without First
with Minto First, via subject
First-level kind
without Business losses
with Minto Business losses
Count
without 3
with Minto 3
All nine correctly placed?
without No; Research and the separate churn chart disappear.
with Minto No; CX/Research are conflated and user posts sit under churn.
Backlog as SCQ complication?
without No
with Minto Both complication and reason, so not stronger.
Format
without Formal memo-style email
with Minto Oversized formal memo
Invented material
without Significant expansion, direct correlation, multiple recent interviews, prospect citations, formal complaint, growing dissatisfaction
with Minto Directly increased churn, immediate pipeline damage, severe frustration, formal complaint, daily compounding
Reader question literal?
without No
with Minto No

Judge’s check	without	with Minto
Answer first	yes	yes
First-level elements	3	3
First-level kind matches the gold	yes	yes
Invented facts	yes	yes
Source lost without a note	yes	yes
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

qwen3.6-35b-a3b 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 16 under blind labels and did not know which one had the skill.

Prompt without Minto 1 438 B

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

<!-- Original paraphrase inspired by Jory MacKay's Planio article,
     "The Pyramid Principle: How to pitch anything (and get a yes)", 2022. -->

# Fixture 08: technical-debt message

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

## Context

You are a product manager writing to Alex, who decides the next sprint's focus.
Available evidence includes a time series of incoming and fixed defects, a
one-year projection, customer-experience data, an interview story, churn
plotted against defect volume, user posts, a complaint from a major account,
and Sales reports about falling close rates.

## Before

```text
Hi Alex,

I am increasingly worried about the defect backlog. The attached chart compares
new defects with the number we close and projects the backlog one year ahead.

Customer Experience and Research also report that defects are contributing to
churn. A second chart places churn beside defect volume, and an interview
illustrates the same issue.

There are signs of brand damage too: user posts, a complaint from a major
account, and Sales reports that these concerns are making deals harder to close.

I recommend using the next sprint to reduce the defect backlog. Let me know what
you think.
```

## Task

Rewrite this as a concise message to Alex using the Minto Pyramid Principle.

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

Prompt with Minto five parts, in order · 29 011 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 08: technical-debt message

Mode: write
Language: en

Context

You are a product manager writing to Alex, who decides the next sprint's focus.
Available evidence includes a time series of incoming and fixed defects, a
one-year projection, customer-experience data, an interview story, churn
plotted against defect volume, user posts, a complaint from a major account,
and Sales reports about falling close rates.

Before

Hi Alex,
                
                I am increasingly worried about the defect backlog. The attached chart compares
                new defects with the number we close and projects the backlog one year ahead.
                
                Customer Experience and Research also report that defects are contributing to
                churn. A second chart places churn beside defect volume, and an interview
                illustrates the same issue.
                
                There are signs of brand damage too: user posts, a complaint from a major
                account, and Sales reports that these concerns are making deals harder to close.
                
                I recommend using the next sprint to reduce the defect backlog. Let me know what
                you think.

Task

Rewrite this as a concise message to Alex using the Minto Pyramid Principle.

The judge’s gold gold.md

Gold 08: technical-debt message

This is an original modern fixture inspired by the cited Planio example, not a
book-derived gold text.

Expected structure

Top: Use the next sprint to reduce the defect backlog.

First-level reasons:

The backlog is growing faster than the team can reduce it.
Defects are driving customer churn.
Defects are damaging brand perception and sales.

Evidence stays beneath its reason: incoming/fixed/projection data under backlog
growth; CX, interview, and churn chart under churn; user posts, account
complaint, and Sales reports under brand and sales.

The recommendation must move from the last paragraph to the first sentence.
Specific percentages, customer names, deadlines, or defect counts are
inventions. A compact colleague message is preferable to a formal memo.

An output that treats backlog growth as the SCQ Complication and uses only the
two external business losses as its key line may be stronger than this gold and
must not be penalized.

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