Overview

Create dt-method-02-research.instructions.md — the method-tier instruction file for Method 2: Design Research. Users gather evidence about the problem through interviews, observation, and data analysis to build empathy and challenge initial assumptions.

Target File

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

Frontmatter

---
description: 'Design Thinking Method 2: Design Research — evidence gathering, empathy building, and assumption testing'
applyTo: '**/.copilot-tracking/dt/**/method-02*'
---

Required Content

Method Purpose

Method 2 builds evidence-based understanding. Users move from assumptions (surfaced in Method 1) to validated knowledge through structured inquiry. The coach helps users design and conduct research that reveals what they don't yet know.

Three Sub-Methods

Two Specialized Hats

Method 2 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-02-research/:

• research-plan.md — Research questions, target participants, methods, schedule
• interview-notes/ — Raw interview transcripts or summaries (per participant)
• observation-log.md — Field observations, contextual findings
• raw-findings.md — Unprocessed data points and quotes

Lo-Fi Quality Enforcement

Method 2 artifacts are raw data:

• Interview notes are rough, not polished transcripts
• Observations are field notes, not analysis reports
• Data points are captured as-is, interpretation happens in Method 3
• Coach resists the urge to synthesize — that's Method 3's job

Mid-Session Subagent Dispatch

During Method 2, the coach may dispatch runSubagent for focused research queries:

• Industry data lookup (market size, regulatory context, competitive landscape)
• Technical constraint research (platform capabilities, API limitations)
• Adjacent problem space exploration (how other teams solved similar problems)

The coach receives subagent results and weaves them into the coaching conversation without breaking session state. This mirrors task-researcher's subagent dispatch pattern.

Coaching Approach

The coach in Method 2:

• Helps design unbiased research questions ("How might you phrase that without leading the respondent?")
• Encourages diverse perspectives ("We've heard from engineering — what might the end user's experience be?")
• Flags confirmation bias ("I notice the research plan only targets people who already use the product")
• Celebrates surprising findings ("That contradicts our earlier assumption — that's valuable data")

Token Budget

Target: ~1,500-2,000 tokens (method tier)

How to Build This File

This is an .instructions.md file — use the prompt-builder agent (not task-implementor) for the authoring phase. The prompt-builder includes built-in Prompt Quality Criteria validation and sandbox testing specific to AI artifacts (.instructions.md, .prompt.md, .agent.md, SKILL.md).

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

Gather source material for the Method 2 (Design Research) instruction file.

Source Material: The upstream Method 2 definitions — research methodology
patterns, empathy techniques, bias mitigation, and interview framing — are
defined in the DT4HVE repository:

design-thinking-for-hve-capabilities/.github/chatmodes/design-thinking.chatmode.md
design-thinking-for-hve-capabilities/guidance/02-design-research.md

The chatmode defines Method 2's role in the 9-method sequence and its two
specialized hats (Research Designer, Empathy Guide). The guidance file contains
the detailed sub-method definitions, subagent dispatch patterns, and coaching
examples. If you don't have the DT4HVE repository cloned, ask a maintainer for
access.

Steps:

1. Type /clear to start a fresh conversation.
2. Attach the DT4HVE chatmode file and 02-design-research.md listed above as context.
3. Copy the prompt below into chat and send.

/task-research topic="DT Method 2 design research for hve-core"

Research the Design Thinking Method 2 (Design Research) patterns for an
.instructions.md file targeting
`.github/instructions/dt-method-02-research.instructions.md`.

Use the attached DT4HVE Design Thinking Coach chatmode and Method 2 guidance
file as primary sources. Extract and analyze:
- Three sub-methods for Method 2 (planning, execution, documentation)
- Two specialized hats: Research Designer and Empathy Guide — activation
  triggers, behaviors, and example coaching prompts
- Research methodology patterns and empathy techniques
- Bias mitigation strategies and interview framing approaches
- Mid-session subagent dispatch patterns for research tasks
- Lo-fi enforcement rules (artifacts stay rough, no polishing)
- Coaching approach: unbiased research questions, diverse perspectives, flags
  confirmation bias

Focus areas:
- How the coach embeds coaching behavior, not procedural steps
- What makes each hat distinct in voice and purpose
- How subagent dispatch extends research capacity mid-session
- How coaching examples can be nativized for AI-assisted context

The research output will feed `/task-plan` and then `/prompt-build` to author
the instructions file.

Output: DT method 02 research research

Phase 2: Plan

Plan the file structure and content organization using the research output.

Steps:

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

/task-plan

Plan the implementation of
`.github/instructions/dt-method-02-research.instructions.md` — a method-tier
instruction file for DT Method 2 (Design Research).

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure
  (`description`, `applyTo: '**/.copilot-tracking/dt/**/method-02*'`)
- Method purpose and overview
- Sub-method table (planning, execution, documentation)
- Two specialized hats (Research Designer, Empathy Guide) with activation
  triggers and example coaching prompts
- Subagent dispatch patterns for mid-session research tasks
- Artifact structure for design research outputs
- Lo-fi enforcement rules
- Coaching approach: unbiased research questions, diverse perspectives, flags
  confirmation bias
- Token budget target: ~1,500-2,000 tokens (method tier)

The implementation phase will use `/prompt-build` (not task-implementor) since
this is an AI artifact file.

Output: .copilot-tracking/plans/{date}-dt-method-02-research-plan.md

Phase 3: Build

Author the instruction file using the prompt-builder agent. Prompt-builder handles authoring standards (frontmatter, writing style, progressive disclosure) automatically through its built-in Prompt Quality Criteria validation.

Steps:

1. Type /clear to reset the conversation.
2. Attach the plan document from Phase 2 (find it in .copilot-tracking/plans/).
3. Copy the prompt below into chat and send.

/prompt-build file=.github/instructions/dt-method-02-research.instructions.md

Build the DT Method 2 (Design Research) instructions file following the
attached implementation plan.

Requirements:
- Method-tier instruction file loaded on `.copilot-tracking/dt/**/method-02*`
  paths
- Three sub-methods defined (planning, execution, documentation)
- Two specialized hats (Research Designer, Empathy Guide) with clear activation
  triggers
- Mid-session subagent dispatch patterns for research tasks
- Lo-fi enforcement: artifacts stay rough, no polishing during research
- Coaching approach embeds behavior (unbiased research questions, diverse
  perspectives, flags confirmation bias) — not procedural steps
- Artifact structure for design research outputs
- Token budget: ~1,500-2,000 tokens
- Nativize DT4HVE content for HVE Core context — avoid source-specific
  references

Output: .github/instructions/dt-method-02-research.instructions.md

Phase 4: Review

Validate the instruction file against the plan and prompt-builder standards.

Steps:

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

/task-review

Review the implementation of
`.github/instructions/dt-method-02-research.instructions.md` against the
attached plan.

Validate:
- Prompt Quality Criteria from `.github/instructions/prompt-builder.instructions.md`
- Three sub-methods defined (planning, execution, documentation)
- Two specialized hats with distinct activation triggers and coaching voices
- Mid-session subagent dispatch patterns are practical and well-defined
- Lo-fi enforcement prevents polishing during research
- Coaching approach: unbiased research questions, diverse perspectives, flags
  confirmation bias
- Token count is within ~1,500-2,000 target (method tier budget)
- Frontmatter has correct `applyTo: '**/.copilot-tracking/dt/**/method-02*'`
  glob
- No temporal markers, task IDs, or DT4HVE-specific references remain
- Writing style follows prompt-builder standards: guidance over commands,
  `*` bullets, `**bold**` for key concepts

Output: .copilot-tracking/reviews/{date}-dt-method-02-research-review.md

After Review

The reviewer reports one of three outcomes:

• Pass — The instruction file meets all criteria. Open a PR with the new file.
• Iterate — The reviewer identified specific issues. Return to Phase 3: /clear, attach the review document, then re-run /prompt-build with the fixes noted.
• Escalate — Fundamental gaps need more research. Return to Phase 1 to investigate the identified areas.

Success Criteria

• File created at .github/instructions/dt-method-02-research.instructions.md
• Frontmatter applyTo targets Method 2 artifact paths
• Three sub-methods defined (planning, execution, documentation)
• Two specialized hats with clear activation triggers
• Mid-session subagent dispatch described for focused research queries
• Lo-fi enforcement: raw data only, no synthesis (that's Method 3)
• Coaching examples demonstrate empathy building and bias mitigation
• Token count within ~1,500-2,000 target
• Passes task-reviewer validation against prompt-builder standards