Overview

Create dt-method-03-synthesis.instructions.md — the method-tier instruction file for Method 3: Input Synthesis. Users transform the raw research data gathered in Method 2 into patterns, insights, and actionable problem statements. This is the final method in the Problem Space before the user either transitions to the Solution Space or hands off to RPI.

Target File

.github/instructions/dt-method-03-synthesis.instructions.md

Frontmatter

---
description: 'Design Thinking Method 3: Input Synthesis — pattern recognition, insight generation, and problem statement articulation'
applyTo: '**/.copilot-tracking/dt/**/method-03*'
---

Required Content

Method Purpose

Method 3 bridges raw data and action. Users process research findings to identify patterns, generate insights, and articulate a well-defined problem statement. The quality of synthesis directly determines the quality of solutions in Methods 4-6.

Three Sub-Methods

Two Specialized Hats

Method 3 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-03-synthesis/:

• affinity-clusters.md — Grouped findings with theme labels
• insight-statements.md — Synthesized insights derived from patterns
• problem-definition.md — Articulated problem statement (not a solution)
• hmw-questions.md — "How Might We" questions bridging problem to solution space

Lo-Fi Quality Enforcement

Method 3 artifacts are rough analytical work:

• Affinity clusters are grouped bullet lists, not polished diagrams
• Insight statements are plain language, not academic findings
• Problem definitions are conversational, not formal requirements
• HMW questions are generative, not evaluated

Problem Space Exit Point

Method 3 is the final Problem Space method. After completion, the coach triggers graduation awareness:

• Continue to Solution Space: Proceed to Method 4 (Brainstorming) with synthesized insights
• Hand off to RPI: Use dt-handoff-problem-space.prompt.md to produce RPI-ready artifact targeting task-researcher
• Revisit earlier methods: Return to Method 1 or 2 if synthesis reveals gaps

This is a critical transition point where the DT Prompt Strategy's "start light" evaluation occurs — assess whether Phase 3's instruction-based approach is sufficient or richer DT-native prompt variants are needed.

Coaching Approach

The coach in Method 3:

• Helps see connections the user might miss ("The operations team and the end users both mentioned wait times — different contexts, same pain point")
• Pushes for depth in insight statements ("That's an observation. What does it mean for the people affected?")
• Resists premature solution thinking ("I notice that reads like a solution — can we reframe it as a problem?")
• Validates synthesis against research data ("Which research findings support that insight?")

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 3 (Input Synthesis) instruction file.

Source Material: The upstream Method 3 definitions — synthesis techniques,
affinity mapping, insight framing patterns, and HMW question formulation — are
defined in the DT4HVE repository:

design-thinking-for-hve-capabilities/.github/chatmodes/design-thinking.chatmode.md
design-thinking-for-hve-capabilities/guidance/03-input-synthesis.md

The chatmode defines Method 3's role in the 9-method sequence, the Problem Space
exit point, and its two specialized hats (Pattern Analyst, Insight Framer). The
guidance file contains the detailed sub-method definitions, HMW question
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 03-input-synthesis.md listed above as context.
3. Copy the prompt below into chat and send.

/task-research topic="DT Method 3 input synthesis for hve-core"

Research the Design Thinking Method 3 (Input Synthesis) patterns for an
.instructions.md file targeting
`.github/instructions/dt-method-03-synthesis.instructions.md`.

Use the attached DT4HVE Design Thinking Coach chatmode and Method 3 guidance
file as primary sources. Extract and analyze:
- Three sub-methods for Method 3 (planning, execution, documentation)
- Two specialized hats: Pattern Analyst and Insight Framer — activation
  triggers, behaviors, and example coaching prompts
- Synthesis techniques: affinity mapping, pattern clustering, insight framing
- HMW (How Might We) question formulation patterns and quality criteria
- Problem Space exit point behavior — what triggers graduation from Problem
  Space to Solution Space
- Lo-fi enforcement rules (artifacts stay rough, no polishing)
- Coaching approach: resists premature solution thinking, guides users toward
  genuine insights

Focus areas:
- How the coach embeds coaching behavior, not procedural steps
- What makes each hat distinct in voice and purpose
- How Problem Space exit behavior prevents premature transitions
- How HMW questions bridge from insights to solution ideation
- How coaching examples can be nativized for HVE Core context

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

Output: DT method 03 synthesis 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-03-synthesis.instructions.md` — a method-tier
instruction file for DT Method 3 (Input Synthesis).

Use the attached research document as the primary input.

The plan should cover:
- Frontmatter structure
  (`description`, `applyTo: '**/.copilot-tracking/dt/**/method-03*'`)
- Method purpose and overview
- Sub-method table (planning, execution, documentation)
- Two specialized hats (Pattern Analyst, Insight Framer) with activation
  triggers and example coaching prompts
- Problem Space exit point behavior and graduation criteria
- HMW question formulation patterns and quality criteria
- Artifact structure for synthesis outputs
- Lo-fi enforcement rules
- Coaching approach: resists premature solution thinking, guides toward genuine
  insights
- 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-03-synthesis-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-03-synthesis.instructions.md

Build the DT Method 3 (Input Synthesis) instructions file following the
attached implementation plan.

Requirements:
- Method-tier instruction file loaded on `.copilot-tracking/dt/**/method-03*`
  paths
- Three sub-methods defined (planning, execution, documentation)
- Two specialized hats (Pattern Analyst, Insight Framer) with clear activation
  triggers
- Problem Space exit point: graduation criteria that prevent premature
  transition to Solution Space
- HMW question formulation with quality criteria
- Lo-fi enforcement: artifacts stay rough, no polishing during synthesis
- Coaching approach embeds behavior (resists premature solution thinking, guides
  toward genuine insights) — not procedural steps
- Artifact structure for synthesis outputs
- Token budget: ~1,500-2,000 tokens
- Nativize DT4HVE content for HVE Core context — avoid source-specific
  references

Output: .github/instructions/dt-method-03-synthesis.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-03-synthesis.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
- Problem Space exit point prevents premature transition to Solution Space
- HMW question formulation patterns are practical and well-defined
- Lo-fi enforcement prevents polishing during synthesis
- Coaching approach: resists premature solution thinking, guides toward genuine
  insights
- Token count is within ~1,500-2,000 target (method tier budget)
- Frontmatter has correct `applyTo: '**/.copilot-tracking/dt/**/method-03*'`
  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-03-synthesis-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-03-synthesis.instructions.md
• Frontmatter applyTo targets Method 3 artifact paths
• Three sub-methods defined (planning, execution, documentation)
• Two specialized hats with clear activation triggers
• Problem Space exit point triggers graduation awareness with three choices
• Artifact includes HMW question generation guidance
• Coach resists premature solution thinking
• Token count within ~1,500-2,000 target
• Passes task-reviewer validation against prompt-builder standards