Overview

Create dt-method-09-deep.instructions.md — the on-demand deep instruction file for Method 9: Iteration at Scale. Loaded explicitly by the coach via read_file when advanced scaling and organizational change expertise is needed. The method-tier file covers adoption measurement basics and scaling patterns; this deep file adds organizational change management (ADKAR), advanced scaling patterns, adoption measurement systems, scaling anti-patterns, and manufacturing-specific deployment patterns.

Target File

.github/instructions/dt-method-09-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 9: Iteration at Scale — organizational change, advanced scaling, adoption measurement, and anti-patterns'
applyTo: ''
---

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

Required Content

Organizational Change Management (Supports Hat 1: Change Strategist)

Scaling validated solutions requires change management rigor:

• ADKAR framework application: Awareness → Desire → Knowledge → Ability → Reinforcement — mapping DT solution rollout to established change management methodology
• Resistance pattern recognition: Common resistance archetypes (skeptic, passive resister, vocal opponent, silent saboteur) and tailored engagement strategies
• Champion network design: Building a network of advocates across roles, shifts, and locations — selection criteria, enablement approach, and sustainment
• Communication planning: Phased announcements, feedback channels, and narrative framing — adapting messaging for different organizational levels
• Organizational memory: Capturing institutional knowledge gained during the DT process so it persists beyond the immediate project team

Advanced Scaling Patterns (Supports Hat 2: Scaling Architect)

Scaling beyond initial deployment:

• Phased rollout design: Sequencing rollout to maximize learning — starting with most receptive groups, then extending to challenging contexts
• Bottleneck identification: Common scaling bottlenecks (training capacity, support resources, infrastructure, management bandwidth) and mitigation strategies
• Edge case scaling: Handling the long tail of special situations that don't fit the standard deployment pattern
• Multi-site deployment: Adapting solutions for different physical locations, team compositions, and local conditions
• Graceful degradation planning: When scaling hits limits, how to maintain core value while accepting reduced scope in some areas

Adoption Measurement Systems (Supports Hat 3: Adoption Analyst)

Tracking whether scaling is succeeding:

• Leading vs. lagging indicators: Behavioral leading indicators (usage frequency, feature adoption, workaround reduction) vs. outcome lagging indicators (productivity, error rates, satisfaction scores)
• Adoption curve analysis: Mapping actual adoption against predicted curves — recognizing when adoption is stalling, accelerating, or plateauing
• Value realization tracking: Connecting adoption metrics to the original DT value proposition — proving that scaled deployment delivers the validated benefits
• Feedback loop design: Structured mechanisms for ongoing user feedback at scale — surveys, usage analytics, support ticket analysis, periodic check-ins
• Failure mode detection: Early warning signals that adoption is failing — workaround emergence, shadow processes, compliance without engagement

Scaling Anti-Patterns

Common ways scaling goes wrong:

• Big bang deployment: Attempting full-scale rollout without phased learning — overwhelms support, generates resistance, risks reputational damage
• Training by memo: Replacing hands-on enablement with documentation-only training — adoption without understanding
• Metrics theater: Tracking metrics that show adoption without measuring actual value delivery — vanity metrics vs. actionable metrics
• Champion burnout: Over-relying on a small number of advocates without rotation, recognition, or relief
• Scope creep during scaling: Adding features or requirements during rollout that weren't part of the validated solution

Manufacturing Deployment Patterns

From DT4HVE manufacturing context:

• Shift-by-shift rollout: Phasing deployment across shifts to maintain production continuity and enable peer learning
• Union and safety committee alignment: Engaging union representatives and safety committees early — addressing concerns about job impact, safety implications, and fair implementation
• Equipment integration sequencing: Deploying in coordination with maintenance windows, equipment upgrades, and production schedules
• Contractor and vendor coordination: Managing deployment when external parties operate equipment or maintain systems affected by the solution

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/09-iteration-at-scale.md
2. .github/instructions/dt-method-09-iteration.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 organizational change management, scaling patterns, adoption measurement, anti-patterns, and manufacturing deployment.

Starter prompt:

/task-research

Research for dt-method-09-deep.instructions.md (on-demand deep file)

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/09-iteration-at-scale.md AND the already-built method-tier file at .github/instructions/dt-method-09-iteration.instructions.md. Extract advanced/deep-dive content that goes BEYOND the basic method-tier coverage:
- Organizational change management — ADKAR application, resistance patterns, champion networks, communication planning
- Advanced scaling patterns — phased rollout, bottleneck identification, multi-site deployment, graceful degradation
- Adoption measurement systems — leading/lagging indicators, adoption curves, value realization, failure mode detection
- Scaling anti-patterns — big bang deployment, training by memo, metrics theater, champion burnout
- Manufacturing deployment patterns from DT4HVE domain expertise

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 — organizational change, scaling patterns, adoption measurement, anti-patterns, manufacturing deployment.
3. Define section ordering, token allocation, and confirm empty applyTo.

Starter prompt:

/task-plan

Plan for dt-method-09-deep.instructions.md (on-demand deep file)

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

- Organizational change management section — ADKAR, resistance patterns, champion networks, communication planning
- Advanced scaling patterns — phased rollout, bottleneck identification, multi-site, graceful degradation
- Adoption measurement systems — leading/lagging indicators, adoption curves, value realization, failure mode detection
- Scaling anti-patterns — five key anti-patterns with recognition signals
- Manufacturing deployment patterns — shift-by-shift rollout, union alignment, equipment integration, contractor coordination
- On-demand loading structure — empty applyTo, loaded via read_file by the coach
- Content must clearly go beyond what the method-tier file already covers
- Section ordering and token budget allocation (~2,000-3,000 tokens)

Output: plan at .copilot-tracking/plans/{date}-dt-method-09-deep-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Content supports three hat roles — organize material so the coach can quickly find relevant advanced content.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-09-deep.instructions.md

Build using the plan at .copilot-tracking/plans/{date}-dt-method-09-deep-plan.md.

This is an on-demand deep instruction file for Method 9: Iteration at Scale. 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
- Organizational change management with ADKAR framework, resistance patterns, champion networks
- Advanced scaling patterns with phased rollout, bottleneck identification, graceful degradation
- Adoption measurement systems with leading/lagging indicators, adoption curves, failure mode detection
- Scaling anti-patterns — five key anti-patterns with recognition signals and mitigation
- Manufacturing deployment patterns — shift-by-shift, union/safety alignment, equipment integration
- 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 hat coverage, change management depth, adoption measurement quality, and prompt-builder compliance.

Starter prompt:

/task-review

Review: .github/instructions/dt-method-09-deep.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- Hat coverage — advanced material supports Change Strategist, Scaling Architect, and Adoption Analyst roles
- Change management depth — ADKAR-based approach with resistance patterns, not generic advice
- Scaling pattern quality — phased rollout with practical bottleneck and degradation strategies
- Adoption measurement rigor — leading/lagging indicator framework with failure mode detection
- Anti-pattern coverage — five named anti-patterns with recognition signals
- Manufacturing deployment contexts — practical factory-floor deployment constraints
- 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 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
• Organized by hat affinity to help the coach locate relevant content quickly

Success Criteria

• File created at .github/instructions/dt-method-09-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Organizational change management with ADKAR framework and resistance pattern recognition
• Advanced scaling patterns with phased rollout and graceful degradation planning
• Adoption measurement systems with leading/lagging indicators and failure mode detection
• Five scaling anti-patterns with recognition signals
• Manufacturing deployment patterns including shift-by-shift rollout and union/safety alignment
• 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