Overview

Create dt-method-06-lofi-prototypes.instructions.md — the method-tier instruction file for Method 6: Low-Fidelity Prototypes. Users build rapid, intentionally rough representations of selected concepts to learn through making. This is the final method in the Solution Space, and the lo-fi enforcement is most critical here — artifacts must signal "still being shaped" to prevent premature commitment.

Target File

.github/instructions/dt-method-06-lofi-prototypes.instructions.md

Frontmatter

---
description: 'Design Thinking Method 6: Low-Fidelity Prototypes — rapid experimentation, lo-fi artifact creation, and feedback planning'
applyTo: '**/.copilot-tracking/dt/**/method-06*'
---

Required Content

Method Purpose

Method 6 makes concepts tangible. Users build quick, rough prototypes that answer specific questions about their concepts. The goal is learning, not building — each prototype tests a hypothesis. This method directly addresses the "Too Nice Prototype" tension from community feedback: artifacts must look unfinished to invite honest feedback and prevent sunk-cost attachment.

Three Sub-Methods

Two Specialized Hats

Prototyping Techniques

The coach selects techniques based on what's being tested:

• Paper prototyping: Sketched interfaces, drawn workflows, hand-drawn storyboards — tests interaction patterns
• Storyboarding: Sequential narrative frames showing a user journey — tests the overall experience flow
• Wizard of Oz: Human simulates the system behavior — tests the concept without building anything
• Role playing: Act out the service or interaction — tests interpersonal dynamics and process flows
• Cardboard prototyping: Physical mock-ups from simple materials — tests spatial and physical interactions

For AI-assisted contexts, prototypes may also include:

• Rough markdown documents representing planned tools or artifacts
• Simple prompt-response examples showing expected coaching interactions
• Draft agent or instruction file skeletons demonstrating behavior patterns

Method 6 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-06-lofi-prototypes/:

• prototypes/ — One folder per prototype: description, hypothesis being tested, prototype artifact(s)
• feedback-plan.md — Who to gather feedback from, questions to ask, response capture format
• learnings-log.md — What each prototype revealed, which hypotheses were validated/invalidated

Lo-Fi Quality Enforcement (Critical)

This is the most important lo-fi enforcement point in the entire process:

• Prototypes must look obviously unfinished — this invites feedback rather than compliments
• The coach actively prevents polish: "That prototype is looking too clean — can we make it rougher? Polished prototypes get 'looks great!' instead of honest feedback."
• Time-box enforcement: prototypes should take minutes to build, not hours
• Artifacts that could be mistaken for finished work are flagged: "This looks like a final design — remember, lo-fi prototypes are throwaway learning tools"
• The "Too Nice Prototype" tension is resolved here — the coach maintains creative roughness

Coaching Approach

The coach in Method 6:

• Celebrates speed over perfection: "The best prototype is the one that teaches you something in 10 minutes"
• Connects prototypes to hypotheses: "This tests the usability assumption — what would you build to test the viability assumption?"
• Prevents sunk-cost thinking: "Remember, we expect to throw most of these away — that's the point"
• Bridges to feedback: "Now that you've built something, who should see it? And what would they tell you that would change your mind?"

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.

Workflow: /task-research → /task-plan → /prompt-build → /task-review
Between each phase, run /clear to reset context.

Phase 1: Research

Source Material: design-thinking-for-hve-capabilities/guidance/06-low-fidelity-prototypes.md
This 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 the source material above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-* instruction files for structural precedent.
4. Gather content on lo-fi prototyping techniques, lo-fi enforcement patterns, feedback planning, and the "Too Nice Prototype" tension.

Starter prompt:

/task-research

Research for IS029: dt-method-06-lofi-prototypes.instructions.md

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/06-low-fidelity-prototypes.md. Extract:
- Lo-fi prototyping techniques (paper prototyping, storyboarding, Wizard of Oz, role playing, cardboard prototyping)
- Lo-fi enforcement patterns — how to keep artifacts deliberately rough
- The "Too Nice Prototype" tension and its resolution strategies
- Feedback planning methods — who to show prototypes to, what questions to ask
- AI-assisted prototyping adaptations (markdown docs, prompt-response examples, draft agent skeletons)

Also read .github/instructions/prompt-builder.instructions.md for authoring standards and any existing dt-method-*.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 instruction file structure — method purpose, three sub-methods, two specialized hats, lo-fi enforcement mechanisms, prototype types, feedback planning.
3. Define section ordering, token allocation, and applyTo targeting.

Starter prompt:

/task-plan

Plan for IS029: dt-method-06-lofi-prototypes.instructions.md

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

- Method purpose: making concepts tangible through rapid, intentionally rough prototypes
- Three sub-methods: 6a Prototype Planning, 6b Prototype Building, 6c Feedback Planning
- Two hats: Prototype Builder, Feedback Designer
- Lo-fi enforcement mechanisms — the defining characteristic of this method
- Prototype types for both physical and AI-assisted contexts
- Feedback planning: hypothesis-driven questions, response capture format
- "Too Nice Prototype" tension resolution strategies
- Section ordering and token budget allocation (~1,500-2,000 tokens)
- applyTo: '**/.copilot-tracking/dt/**/method-06*'

Output: plan at .copilot-tracking/plans/{date}-is029-dt-method-06-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Lo-fi enforcement is the defining characteristic — ensure it pervades the entire file, not just one section.

Starter prompt:

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

Build IS029 using the plan at .copilot-tracking/plans/{date}-is029-dt-method-06-plan.md.

This is a method-tier instruction file for Method 6: Low-Fidelity Prototypes. Key authoring notes:
- applyTo targets Method 6 artifact paths: '**/.copilot-tracking/dt/**/method-06*'
- Lo-fi enforcement is the DEFINING characteristic — it must pervade the entire file
- The coach actively prevents polish: "That prototype is looking too clean"
- Time-box enforcement: prototypes should take minutes, not hours
- "Too Nice Prototype" tension is explicitly addressed and resolved
- Three sub-methods with consistent table structure
- Two specialized hats with activation triggers
- Prototyping techniques cover both physical and AI-assisted contexts
- Feedback planning connects prototypes to hypotheses
- Coaching tone celebrates speed over perfection

Phase 4: Review

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate lo-fi enforcement strength, prototyping technique coverage, feedback planning quality, and "Too Nice Prototype" tension resolution.

Starter prompt:

/task-review

Review IS029: .github/instructions/dt-method-06-lofi-prototypes.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- Lo-fi enforcement strength — this should be the strongest enforcement in the curriculum
- Prototyping technique coverage for both physical and AI-assisted contexts
- Feedback planning quality — hypothesis-driven, not generic show-and-tell
- "Too Nice Prototype" tension resolution — explicitly addressed
- Time-box enforcement for prototype construction
- Token budget: ~1,500-2,000 tokens
- Frontmatter applyTo correctness
- Three sub-methods and two hats with consistent table structure

After Review

• Pass: Mark IS029 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:

• applyTo targets Method 6 artifact paths
• Three sub-methods with consistent table structure
• Two specialized hats with activation triggers
• Lo-fi enforcement is a first-class concern, not an afterthought

Success Criteria

• File created at .github/instructions/dt-method-06-lofi-prototypes.instructions.md
• Frontmatter applyTo targets Method 6 artifact paths
• Three sub-methods defined (planning, building, feedback planning)
• Two specialized hats with clear activation triggers
• Prototyping techniques cover both physical and AI-assisted contexts
• Lo-fi quality enforcement is the strongest in the curriculum — addresses "Too Nice Prototype" tension
• Feedback planning guidance connects prototypes to hypotheses
• Token count within ~1,500-2,000 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