Overview

Create dt-method-06-deep.instructions.md — the on-demand deep instruction file for Method 6: Low-Fidelity Prototypes. Loaded explicitly by the coach via read_file when advanced prototyping expertise is needed: complex prototype planning for multi-component systems, service blueprinting, experience prototyping techniques, and advanced feedback session design.

Target File

.github/instructions/dt-method-06-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 6: Low-Fidelity Prototypes — paper prototyping, service blueprinting, and advanced feedback design'
applyTo: ''
---

Note: applyTo is empty — this file is loaded on-demand by the coach agent, not auto-loaded by glob.

Required Content

Advanced Paper Prototyping

Beyond basic sketches:

• Interactive paper prototypes: Cut-out UI elements that can be rearranged, layered, and "clicked" by moving pieces
• State-based prototyping: Multiple states of the same interface laid out sequentially — shows before/during/after interactions
• Contextual paper prototypes: Prototypes that include the environment (desk layout, conversation flow, process steps) not just the artifact
• Template libraries: Reusable shapes, icons, and patterns that speed up paper prototype creation while maintaining lo-fi aesthetic

Service Blueprinting

For complex multi-touchpoint concepts:

• Blueprint structure: Customer actions → frontstage interactions → backstage processes → support systems (4-layer mapping)
• Failure point identification: Mark each touchpoint with potential failure modes and recovery paths
• Moment-of-truth mapping: Identify critical interactions where the experience succeeds or fails
• Cross-channel alignment: How does the service flow when users switch between channels (mobile, desktop, in-person)?

Experience Prototyping

Testing the experience, not just the artifact:

• Bodystorming: Physically acting out the service experience in a simulated environment
• Desktop walkthrough: Using miniatures or props to walk through complex systems
• Day-in-the-life simulation: Full timeline prototype showing how the concept integrates into daily workflows
• Emotional journey mapping: Overlaying emotional states onto the prototype timeline — where does the user feel confident, confused, frustrated?

Advanced Feedback Session Design

Beyond basic "show and tell":

• A/B prototype testing: Show two prototype variants and ask comparative questions
• Think-aloud protocols: Users narrate their thinking as they interact with the prototype
• Love/wish/wonder framework: "What do you love? What do you wish was different? What do you wonder about?" — structures feedback without leading
• Feedback synthesis patterns: How to consolidate feedback from multiple sessions into actionable prototype iterations
• Hostile user testing: Deliberately invite critics and skeptics — their feedback is the most valuable at this stage

Manufacturing-Specific Prototyping

Adapted from DT4HVE manufacturing context:

• Process flow prototyping: Map production line changes with sticky notes on a whiteboard before any system modifications
• Shift handoff simulation: Prototype information flow across shift changes using role-play
• Safety constraint testing: Prototype safety-critical interactions with extra scrutiny on failure modes
• Operator perspective prototypes: Build prototypes at operator eye level, in simulated noise/distraction conditions

Token Budget

Target: ~2,000-3,000 tokens (on-demand 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, run /clear to reset context.

Phase 1: Research

Source Material:

1. design-thinking-for-hve-capabilities/guidance/06-low-fidelity-prototypes.md
2. .github/instructions/dt-method-06-lofi-prototypes.instructions.md (already-built method-tier file)

The DT4HVE guidance file lives in the DT4HVE repository. If you don't have local access, ask the user to provide it or use read_file if the repo is cloned nearby.

Steps:

1. Read both source materials above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-*-deep instruction files for structural precedent.
4. Gather content on paper prototyping techniques, service blueprinting, experience prototyping, and feedback session design for lo-fi artifacts.

Starter prompt:

/task-research

Research for IS032: dt-method-06-deep.instructions.md (on-demand deep file)

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/06-low-fidelity-prototypes.md AND the already-built method-tier file at .github/instructions/dt-method-06-lofi-prototypes.instructions.md. Extract advanced/deep-dive content that goes BEYOND the basic method-tier coverage:
- Advanced paper prototyping techniques — interactive paper prototypes, state-based prototyping, contextual prototypes, template libraries
- Service blueprinting — 4-layer structure, failure point identification, moment-of-truth mapping, cross-channel alignment
- Experience prototyping — bodystorming, desktop walkthrough, day-in-the-life simulation, emotional journey mapping
- Advanced feedback session design — A/B prototype testing, think-aloud protocols, love/wish/wonder framework, hostile user testing

Also read .github/instructions/prompt-builder.instructions.md for authoring standards and any existing dt-method-*-deep.instructions.md files for structural precedent.

Output: research summary from Phase 1 above

Phase 2: Plan

Steps:

1. Review the research output from Phase 1.
2. Plan the deep instruction file structure — advanced prototyping techniques (paper, service blueprint, experience), feedback session orchestration, on-demand loading structure.
3. Define section ordering, token allocation, and confirm empty applyTo.

Starter prompt:

/task-plan

Plan for IS032: dt-method-06-deep.instructions.md (on-demand deep file)

Using the Phase 1 research output, plan the deep instruction file:

- Advanced paper prototyping — interactive, state-based, contextual, template libraries
- Service blueprinting — 4-layer structure, failure points, moments of truth, cross-channel alignment
- Experience prototyping — bodystorming, desktop walkthrough, day-in-the-life, emotional journey mapping
- Advanced feedback session design — A/B testing, think-aloud, love/wish/wonder, hostile user testing, synthesis patterns
- Manufacturing-specific prototyping patterns from DT4HVE context
- On-demand loading structure — empty applyTo, loaded via read_file by the coach
- CRITICAL: maintain lo-fi quality even in advanced techniques — "advanced" means more sophisticated learning, not higher fidelity
- Section ordering and token budget allocation (~2,000-3,000 tokens)

Output: plan at .copilot-tracking/plans/{date}-is032-dt-method-06-deep-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Maintain lo-fi quality even in advanced techniques — "advanced" means more sophisticated learning, not higher fidelity.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-06-deep.instructions.md

Build IS032 using the plan at .copilot-tracking/plans/{date}-is032-dt-method-06-deep-plan.md.

This is an on-demand deep instruction file for Method 6: Low-Fidelity Prototypes. Key authoring notes:
- applyTo is EMPTY — this file is loaded on-demand by the coach, not auto-loaded by glob
- Content provides advanced/deep-dive material beyond the basic method-tier file
- Advanced paper prototyping — interactive, state-based, contextual prototypes with template libraries
- Service blueprinting — 4-layer structure with failure points and moments of truth
- Experience prototyping — bodystorming, desktop walkthrough, day-in-the-life simulation
- Advanced feedback session design — A/B testing, think-aloud, love/wish/wonder, hostile user testing
- Manufacturing-specific prototyping patterns (process flow, shift handoff, safety constraints)
- CRITICAL: "advanced" means more sophisticated LEARNING, not higher fidelity — lo-fi quality must be maintained
- Writing style: guidance over commands — deep reference material, not procedural steps
- Token budget: ~2,000-3,000 tokens

Phase 4: Review

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate advanced prototyping depth, lo-fi maintenance in advanced context, service blueprint quality, feedback session design, and prompt-builder compliance.

Starter prompt:

/task-review

Review IS032: .github/instructions/dt-method-06-deep.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- Advanced prototyping depth — must go beyond what the method-tier file already covers
- Lo-fi maintenance in advanced context — "advanced" ≠ higher fidelity
- Service blueprint quality — 4-layer structure is clear and actionable
- Feedback session design — A/B testing, think-aloud, love/wish/wonder are practical
- Manufacturing-specific patterns are grounded in DT4HVE context
- Empty applyTo in frontmatter (on-demand loading)
- Writing style: guidance over commands
- Token budget: ~2,000-3,000 tokens
- Structural consistency with other deep-tier instruction files

After Review

• Pass: Mark IS032 complete.
• Iterate: Address review findings, rebuild, re-review.
• Escalate: If blocked by missing DT4HVE source material or architectural questions, raise to the user.

Authoring Standards

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

• Empty applyTo: since this is on-demand content
• Writing style: guidance over commands
• "Advanced" prototyping ≠ higher fidelity — advanced means better learning from lo-fi artifacts

Success Criteria

• File created at .github/instructions/dt-method-06-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced paper prototyping with interactive and state-based techniques
• Service blueprinting framework with 4-layer structure
• Experience prototyping techniques for testing the experience, not just the artifact
• Advanced feedback session design beyond basic show-and-tell
• Manufacturing-specific prototyping patterns from DT4HVE
• Token count within ~2,000-3,000 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