Overview

Create dt-method-02-deep.instructions.md, the on-demand deep instruction file for Method 2: Design Research. Provides advanced techniques for research design, empathic interviewing, ethnographic observation, and evidence triangulation when the standard method-tier instruction is insufficient.

Target File

.github/instructions/dt-method-02-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 2: Design Research — advanced interview techniques, ethnographic observation, and evidence triangulation'
applyTo: ''
---

Required Content

Advanced Interview Techniques

• Laddering questions: Moving from surface observations to underlying motivations ("Why is that important to you?" repeated with sensitivity)
• Critical incident technique: Ask about specific moments of success or failure rather than general opinions
• Projective techniques: "If this system were a person, how would you describe it?", useful for surfacing unspoken feelings about processes
• Context-triggered interviews: Conducting interviews in the problem environment rather than meeting rooms
• Group dynamics management: Handling dominant voices, silent participants, and conflicting perspectives in group settings

Ethnographic Observation Methods

• Contextual inquiry: Observe users in their work environment, asking questions in the moment
• Day-in-the-life mapping: Track a stakeholder's full workflow to identify pain points that interviews miss
• Artifact analysis: What tools, workarounds, sticky notes, and informal processes reveal about the real workflow
• Shadow observation: Follow a process end-to-end, noting handoffs, delays, and information gaps

Evidence Triangulation

• Multi-source validation: Cross-reference interview data, observation data, and quantitative metrics
• Contradiction analysis: When sources disagree, the contradiction itself is a finding worth documenting
• Saturation detection: Coaching guidance for recognizing when additional research is producing diminishing returns
• Bias audit checklist: Systematic review of research design for confirmation bias, selection bias, and anchoring

Manufacturing Research Patterns

• Shift observation protocols: Research design that accounts for different behaviors across shifts
• Safety-constrained research: How to conduct observation and interviews in environments with safety restrictions
• Operator vs. engineer perspectives: Deliberately seeking both groups to surface the gap between designed and actual workflows
• Machine-human interface observation: Watching operators interact with equipment to surface usability issues invisible in interviews

Token Budget

Target: ~2,000-3,000 tokens (on-demand tier)

Source Material

Attach these files as context for the task-researcher phase:

• DT4HVE Method guidance: design-thinking-for-hve-capabilities/guidance/02-design-research.md, canonical Method 2 with healthcare environment constraints (L81)
• Coaching hats: design-thinking-for-hve-capabilities/.github/chatmodes/hats/, method-specific coaching hat files
• Cumulative research: Design Thinking cumulative research, Parts 1-2 (methodology foundations and cross-industry evidence) and Part 7 (cross-industry evidence and industry context patterns)

RPI Pipeline Workflow

1. task-researcher: Gather DT4HVE advanced Method 2 content, interview frameworks, ethnographic patterns, manufacturing research examples. Cross-reference cumulative research Parts 1-2 (methodology) and Part 7 (cross-industry evidence).
2. task-planner: Plan the file, interview techniques, observation methods, triangulation framework, industry-specific patterns.
3. task-implementor: Author following prompt-builder standards. Techniques should be practical and coachable, not academic.
4. task-reviewer: Validate research methodology depth, coaching applicability, manufacturing reference quality, prompt-builder compliance.

Starter Prompts

Research: /task-research — "Gather advanced Method 2: Design Research content from DT4HVE — interview frameworks, ethnographic observation, evidence triangulation, manufacturing research patterns. Attach guidance/02-design-research.md and cumulative research Parts 1-2, 7 as context."

Plan: /task-plan — "Plan dt-method-02-deep.instructions.md — advanced interview techniques, observation methods, triangulation framework, industry-specific research patterns."

Implement: /task-implement — "Author dt-method-02-deep.instructions.md following prompt-builder standards with empty applyTo, guidance-over-commands tone, 2000-3000 token budget."

Review: /task-review — "Validate dt-method-02-deep.instructions.md against prompt-builder standards, coaching tone, and research methodology depth."

Prompt-Builder Compliance Checklist

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

• description: frontmatter present and descriptive
• applyTo: '' (empty, on-demand loading)
• Writing style uses guidance over commands (no "You must/will/shall")
• Token count within budget tier
• No ALL CAPS emphasis
• Content structured for coaching context

Success Criteria

• File created at .github/instructions/dt-method-02-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced interview techniques (laddering, critical incident, projective, context-triggered)
• Ethnographic observation methods (contextual inquiry, day-in-life, artifact analysis)
• Evidence triangulation with bias audit guidance
• Manufacturing-specific research patterns
• Token count within ~2,000-3,000 target
• Passes task-reviewer validation against prompt-builder standards
• Artifact registered in collections/design-thinking.collection.yml with path and kind fields
• Artifact registered in collections/hve-core-all.collection.yml with path and kind fields
• npm run plugin:generate run after updating collection manifests