Overview

Create dt-method-08-testing.instructions.md — the method-tier instruction file for Method 8: User Testing. Users test their hi-fi prototypes with real or representative users to gather evidence for refinement decisions. Method 8 is critical for supporting non-linear loops — testing results may trigger returns to Method 2 (Research), Method 4 (Brainstorming), or any earlier method when test findings invalidate core assumptions.

Target File

.github/instructions/dt-method-08-testing.instructions.md

Frontmatter

---
description: 'Design Thinking Method 8: User Testing — evidence-based evaluation, test protocols, and non-linear iteration support'
applyTo: '**/.copilot-tracking/dt/**/method-08*'
---

Required Content

Method Purpose

Method 8 puts prototypes in front of users and gathers evidence. Unlike Method 6's feedback planning (which was lo-fi), Method 8 conducts structured testing with functional prototypes. Test results drive one of three outcomes: iterate (Method 9), revisit (return to an earlier method), or validate (proceed to Implementation Space exit).

Three Sub-Methods

Two Specialized Hats

Non-Linear Iteration Loops

Method 8 is the primary trigger for non-linear navigation. Test results may reveal:

The coach helps users interpret findings honestly: "Testing revealed that users don't understand the core value proposition. That's a Method 4 finding, not a Method 9 tweak — should we revisit our concepts?"

Test Protocol Design

Structured testing approaches the coach can guide:

• Task-based testing: Users attempt specific tasks while the coach helps observe completion rate, time, and error patterns
• A/B comparison testing: Two prototype variants tested against the same criteria
• Think-aloud testing: Users narrate their thinking during interaction
• Wizard of Oz testing: Parts of the prototype are simulated by a human — tests concept viability before full build
• Longitudinal testing: Extended use over days/weeks — reveals adoption patterns (when feasible)

Method 8 Artifacts

Outputs stored at .copilot-tracking/dt/{project-slug}/method-08-testing/:

• test-protocol.md — Testing methodology, participant profiles, success criteria
• test-sessions/ — Per-session notes, observations, and raw data
• results-analysis.md — Synthesized findings, patterns, and statistical observations
• decision-log.md — Iterate, revisit, or validate decisions with supporting evidence

Coaching Approach

The coach in Method 8:

• Designs rigorous tests: "A yes/no question won't tell us much — what open-ended tasks would reveal how users actually behave?"
• Prevents confirmation bias: "I notice we're focusing on the positive results — what about the 3 users who abandoned the task?"
• Supports difficult decisions: "The data suggests the concept needs significant changes. That's not a failure — it's evidence that saves you from building the wrong thing."
• Facilitates loop decisions: "This finding goes deeper than a UI tweak. Should we take this back to Method 4 and reconsider the concept?"

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, run /clear to reset context.

Phase 1: Research

Gather source material for the user testing method instruction file.

Source Material: design-thinking-for-hve-capabilities/guidance/08-user-testing.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 testing methodologies, non-linear loop patterns, bias mitigation in testing, and evidence interpretation frameworks.

Starter prompt:

/task-research

Research for IS034: dt-method-08-testing.instructions.md

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/08-user-testing.md. Extract:
- Testing methodologies (usability testing, A/B testing, cognitive walkthrough, heuristic evaluation)
- Non-linear loop patterns — how testing results feed back to earlier phases
- Bias mitigation in testing — confirmation bias, leading questions, observer effects
- Evidence interpretation frameworks for making go/no-go decisions
- Test protocol types and when to apply each

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

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

Steps:

1. Review the research output from Phase 1.
2. Plan the instruction file structure — method purpose, three sub-methods, two specialized hats, non-linear loop table, test protocol types, decision framework.
3. Define section ordering, token allocation, and applyTo targeting.

Starter prompt:

/task-plan

Plan for IS034: dt-method-08-testing.instructions.md

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

- Method purpose: validating prototypes through structured user testing
- Three sub-methods: 8a Test Planning, 8b Test Execution, 8c Evidence Interpretation
- Two hats: Test Facilitator, Evidence Interpreter
- Non-linear loop table mapping test findings to earlier DT phases
- Test protocol types with selection guidance
- Decision framework for go/iterate/pivot based on test results
- Bias mitigation coaching integrated throughout
- Section ordering and token budget allocation (~1,500-2,000 tokens)
- applyTo: '**/.copilot-tracking/dt/**/method-08*'

Output: plan at .copilot-tracking/plans/{date}-is034-dt-method-08-plan.md

Phase 3: Build

Author the instruction file using the prompt-builder agent.

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Non-linear iteration support is the defining feature — ensure the loop table and coaching guidance empower honest interpretation.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-08-testing.instructions.md

Build IS034 using the plan at .copilot-tracking/plans/{date}-is034-dt-method-08-plan.md.

This is a method-tier instruction file for Method 8: User Testing. Key authoring notes:
- applyTo targets Method 8 artifact paths: '**/.copilot-tracking/dt/**/method-08*'
- Non-linear iteration support is the defining feature — the loop table and coaching guidance must empower honest interpretation
- Three sub-methods with consistent table structure
- Two specialized hats with activation triggers
- Non-linear loop table connecting test findings back to earlier DT phases
- Bias mitigation coaching woven throughout — not a separate section
- Test protocol types with clear selection criteria
- Decision framework: go/iterate/pivot with evidence thresholds
- Coaching examples demonstrate honest evidence interpretation over confirmation bias

Phase 4: Review

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

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate non-linear loop support, testing rigor, bias mitigation, and structural compliance.

Starter prompt:

/task-review

Review IS034: .github/instructions/dt-method-08-testing.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- Non-linear loop support — loop table maps findings to earlier phases
- Testing rigor — protocol types are well-differentiated with selection criteria
- Bias mitigation — coaching addresses confirmation bias, leading questions, observer effects
- Decision framework clarity with evidence thresholds
- Token budget: ~1,500-2,000 tokens
- Frontmatter applyTo correctness
- Three sub-methods and two hats with consistent table structure

After Review

• Pass: Mark IS034 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 8 artifact paths
• Three sub-methods with consistent table structure
• Two specialized hats with activation triggers
• Non-linear iteration loops are first-class concerns

Success Criteria

• File created at .github/instructions/dt-method-08-testing.instructions.md
• Frontmatter applyTo targets Method 8 artifact paths
• Three sub-methods defined (planning, execution, analysis)
• Two specialized hats with clear activation triggers
• Non-linear iteration loop table mapping findings to revisit targets
• Test protocol design covering task-based, A/B, think-aloud, and Wizard of Oz approaches
• Coaching examples support honest interpretation and difficult decisions to revisit earlier methods
• 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