Overview

Create a reference learning scenario based on a manufacturing context that the dt-learning-tutor uses to ground exercises and examples across all 9 DT methods. The scenario follows a factory floor improvement project — relatable, concrete, and complex enough to demonstrate every method meaningfully. Curriculum practice exercises (#617) reference this scenario for continuity, so learners build understanding progressively rather than encountering disconnected examples.

Target File

.github/instructions/dt-curriculum-scenario-manufacturing.instructions.md

Frontmatter

---
description: 'Manufacturing reference scenario for DT learning — factory floor improvement project used across all 9 curriculum modules'
applyTo: '**/.copilot-tracking/dt/**/curriculum-*'
---

Required Content

Scenario Overview

A manufacturing plant is experiencing quality issues on a production line. The scenario provides:

• Context: Mid-size manufacturer, mixed automation and manual processes, multiple shifts
• Problem signal: Rising defect rates, operator frustration, customer complaints
• Stakeholders: Line operators, shift supervisors, quality engineers, plant manager, customers
• Complexity: Technical (equipment), human (training, fatigue), organizational (shift handoffs), and external (customer expectations) dimensions

The scenario is deliberately multi-dimensional so every DT method has meaningful material to work with.

Per-Method Scenario Content

Each method gets scenario-specific material for exercises:

Fictional Data Sets

Include small fictional data sets the tutor can present during exercises:

• Interview excerpt snippets (3-5 per stakeholder type, 2-3 sentences each)
• Affinity map data points (15-20 short observations for clustering)
• Test result summaries (5-8 test scenarios with mixed pass/fail outcomes)

Keep data sets compact — enough for meaningful exercises without overwhelming the instruction file.

Scenario Continuity

The scenario flows logically through all 9 methods. Each module's exercise builds on previous outputs:

• Scoping defines what Research investigates
• Research produces data that Synthesis analyzes
• Synthesis insights feed Brainstorming
• And so on through Handoff

The tutor references previous exercise outputs when advancing to the next module, reinforcing the cumulative nature of the DT methodology.

Token Budget

Target: ~2,000-2,500 tokens (loaded alongside curriculum modules as reference context)

How to Build This File

This is an .instructions.md file — use the prompt-builder agent (not task-implementor) for the authoring phase.

Workflow: /task-research → /task-plan → /prompt-build → /task-review

Between each phase, use /clear to reset context, then attach the output artifact from the previous phase as input for the next.

Phase 1: Research

Research manufacturing improvement scenarios suitable for DT application.

Source Material: DT methodology and scenario design — #file:.github/instructions/prompt-builder.instructions.md for authoring standards, the DT4HVE source materials for scenario patterns, and the curriculum files (#617) for per-method exercise requirements that the scenario must support.

Steps:

1. Type /clear to start a fresh conversation.
2. Attach #file:.github/instructions/prompt-builder.instructions.md and any available curriculum file drafts.
3. Copy the prompt below into chat and send.

/task-research topic="DT manufacturing reference scenario"

Research manufacturing improvement scenarios suitable for a Design Thinking
learning reference.

Extract:
- Manufacturing process improvement patterns (quality, efficiency, safety)
- Stakeholder types in manufacturing contexts (operators, supervisors, engineers)
- Problem dimensions (technical, human, organizational, external)
- Per-method exercise requirements from the curriculum specification
- Fictional data set patterns (interview excerpts, observations, test results)
- Prompt-builder compliance requirements for .instructions.md files

Output: DT manufacturing scenario research

Phase 2: Plan

Plan the scenario with per-method content and fictional data sets.

Steps:

1. Type /clear to reset the conversation.
2. Attach the research document from Phase 1.
3. Copy the prompt below into chat and send.

/task-plan

Plan the manufacturing reference learning scenario.

Use the attached research document as input. The plan should cover:
- Factory context (plant type, processes, shifts, stakeholders)
- Problem signal (defect types, operator frustration, customer complaints)
- Per-method scenario content for all 9 methods with exercises
- Fictional data sets (interview excerpts, affinity data, test results)
- Scenario continuity thread connecting all 9 methods progressively
- Token budget (~2,000-2,500)

Output: .copilot-tracking/plans/{date}-dt-manufacturing-scenario-plan.md

Phase 3: Build

Author the scenario instruction file using prompt-builder.

Steps:

1. Type /clear to reset the conversation.
2. Attach the plan document from Phase 2.
3. Copy the prompt below into chat and send.

/prompt-build

Build the manufacturing reference scenario following the attached plan.

Create .github/instructions/dt-curriculum-scenario-manufacturing.instructions.md:
- Frontmatter: description, applyTo targeting all curriculum artifact paths
- Scenario overview (context, problem, stakeholders, complexity dimensions)
- Per-method content with exercises for all 9 methods
- Fictional data sets (interview excerpts, affinity data points, test results)
- Scenario flows logically through all 9 methods with continuity
- Data is realistic but obviously fictional
- Exercises completable in 5-10 minutes each

Output: .github/instructions/dt-curriculum-scenario-manufacturing.instructions.md

Phase 4: Review

Validate scenario continuity and exercise quality.

Steps:

1. Type /clear to reset the conversation.
2. Attach the plan document from Phase 2.
3. Copy the prompt below into chat and send.

/task-review

Review the manufacturing reference scenario against the attached plan.

Validate:
- Frontmatter has description and applyTo targeting curriculum paths
- Scenario overview establishes context, problem, stakeholders, complexity
- Per-method content provides meaningful exercises for all 9 methods
- Fictional data sets included (interviews, affinity data, test results)
- Scenario flows logically through all 9 methods with continuity
- Exercises are completable in 5-10 minutes each
- Token count within ~2,000-2,500 target
- Prompt-builder compliance verified

Output: .copilot-tracking/reviews/{date}-dt-manufacturing-scenario-review.md

After Review

• Pass — Open a PR with the scenario file.
• Iterate — Return to Phase 3 with the review document to fix identified issues.
• Escalate — Return to Phase 1 to investigate scenario design gaps.

Authoring Standards

Follow .github/instructions/prompt-builder.instructions.md:

• applyTo targets all curriculum artifact paths (loaded alongside curriculum modules)
• Consistent per-method structure
• Fictional data is clearly presented as example data, not real

Success Criteria

• File created at .github/instructions/dt-curriculum-scenario-manufacturing.instructions.md
• Frontmatter includes description and applyTo targeting curriculum paths
• Scenario overview establishes context, problem, stakeholders, and complexity dimensions
• Per-method content provides meaningful exercises for all 9 methods
• Fictional data sets included (interviews, affinity data, test results)
• Scenario flows logically through all 9 methods with continuity
• Exercises are completable in 5-10 minutes each
• Token count within ~2,000-2,500 target
• Passes task-reviewer validation against prompt-builder standards
• Each prompt, instructions, or agent file registered in collections/design-thinking.collection.yml with path and kind fields
• Each prompt, instructions, or agent file registered in collections/hve-core-all.collection.yml with path and kind fields
• npm run plugin:generate succeeds after collection manifest updates