Skip to content

feat(agents): add DT coach agent with tiered instruction loading#656

Merged
agreaves-ms merged 24 commits intomicrosoft:mainfrom
chaosdinosaur:feat/579-dt-coach-agent
Feb 19, 2026
Merged

feat(agents): add DT coach agent with tiered instruction loading#656
agreaves-ms merged 24 commits intomicrosoft:mainfrom
chaosdinosaur:feat/579-dt-coach-agent

Conversation

@chaosdinosaur
Copy link
Collaborator

@chaosdinosaur chaosdinosaur commented Feb 18, 2026

Pull Request

Description

Add dt-coach.agent.md as the single conversational Design Thinking coaching agent.

  • Implement Think/Speak/Empower coaching philosophy governing all responses
  • Define tiered instruction loading: ambient (automatic), method (pattern-matched), on-demand (read_file)
  • Reference all four ambient-tier instruction files (identity, quality, sequencing, state)
  • Implement hat-switching logic for seamless method transitions
  • Integrate progressive hint engine with 4-level escalation
  • Add session management with coaching state initialization and recovery
  • Define method routing with non-linear iteration support
  • Include context refresh protocol and artifact management

Note

This PR depends on #642, #645, #650, #651, #652, #653 (Phase 1 foundation) and #654 (coaching state protocol) being merged first.

Related Issue(s)

Closes #579

Type of Change

Select all that apply:

Code & Documentation:

  • Bug fix (non-breaking change fixing an issue)
  • New feature (non-breaking change adding functionality)
  • Breaking change (fix or feature causing existing functionality to change)
  • Documentation update

Infrastructure & Configuration:

  • GitHub Actions workflow
  • Linting configuration (markdown, PowerShell, etc.)
  • Security configuration
  • DevContainer configuration
  • Dependency update

AI Artifacts:

  • Reviewed contribution with prompt-builder agent and addressed all feedback
  • Copilot instructions (.github/instructions/*.instructions.md)
  • Copilot prompt (.github/prompts/*.prompt.md)
  • Copilot agent (.github/agents/*.agent.md)
  • Copilot skill (.github/skills/*/SKILL.md)

Other:

  • Script/automation (.ps1, .sh, .py)
  • Other (please describe):

Testing

Checklist

Required Checks

  • Documentation is updated (if applicable)
  • Files follow existing naming conventions
  • Changes are backwards compatible (if applicable)
  • Tests added for new functionality (if applicable)

Required Automated Checks

The following validation commands must pass before merging:

  • Markdown linting: npm run lint:md
  • Spell checking: npm run spell-check
  • Frontmatter validation: npm run lint:frontmatter
  • Skill structure validation: npm run validate:skills
  • Link validation: npm run lint:md-links
  • PowerShell analysis: npm run lint:ps

Security Considerations

  • This PR does not contain any sensitive or NDA information
  • Any new dependencies have been reviewed for security issues
  • Security-related scripts follow the principle of least privilege

Additional Notes

🎴 Generated by Copilot

Single conversational agent implementing Think/Speak/Empower philosophy, hat-switching, progressive hint engine, and session management for the 9-method DT framework

Closes microsoft#579
🎓 - Generated by Copilot
Copilot AI review requested due to automatic review settings February 18, 2026 02:16
@chaosdinosaur chaosdinosaur requested a review from a team as a code owner February 18, 2026 02:16
@codecov-commenter
Copy link

codecov-commenter commented Feb 18, 2026

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 85.82%. Comparing base (5a5be4e) to head (b0047f8).

Additional details and impacted files

Impacted file tree graph

@@            Coverage Diff             @@
##             main     #656      +/-   ##
==========================================
- Coverage   85.84%   85.82%   -0.03%     
==========================================
  Files          24       24              
  Lines        4769     4769              
==========================================
- Hits         4094     4093       -1     
- Misses        675      676       +1     
Flag Coverage Δ
pester 85.82% <ø> (-0.03%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.
see 1 file with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR introduces a new Design Thinking coaching agent (dt-coach.agent.md) that implements a conversational coaching workflow for guiding teams through 9 Design Thinking methods. The agent establishes a Think/Speak/Empower coaching philosophy, implements tiered instruction loading (ambient, method-tier, on-demand), and provides session management capabilities with coaching state persistence. This is part of a larger Design Thinking for HVE initiative (Phase 2 per issue #579) that depends on foundation instruction files from Phase 1.

Changes:

  • Add dt-coach.agent.md with coaching philosophy, session management, and method routing guidance
  • Define tiered instruction loading system with references to 4 ambient instruction files
  • Implement hat-switching, progressive hint engine, and artifact management patterns
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings February 18, 2026 02:35
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
chaosdinosaur and others added 2 commits February 17, 2026 18:36
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 4 comments.

Copilot AI review requested due to automatic review settings February 18, 2026 02:52
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings February 18, 2026 02:56
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 4 comments.

Copilot AI review requested due to automatic review settings February 18, 2026 03:30
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

@chaosdinosaur chaosdinosaur changed the base branch from main to epic/design-thinking-coaching February 18, 2026 16:59
chaosdinosaur and others added 7 commits February 18, 2026 09:06
Move dt-coach.agent.md to .github/agents/design-thinking/ to align
with collection-based directory organization per microsoft#643.

Update collection YAML path and regenerate plugin outputs.

🔀 - Generated by Copilot
…agent

- align with writing-style.instructions.md conventions
- use colons for explanations and periods for emphasis

✏️ - Generated by Copilot
Removed the 'dt-coach' entry from the README, which described a Design Thinking coach.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@WilliamBerryiii
Copy link
Member

Thank you for your contribution, @chaosdinosaur. We restructured the PR description to follow the project's pull request template. Please review the updated description and check any additional boxes that apply to your changes.

@chaosdinosaur chaosdinosaur changed the base branch from epic/design-thinking-coaching to main February 18, 2026 21:49
chaosdinosaur and others added 3 commits February 18, 2026 14:34
# Conflicts:
#	collections/design-thinking.collection.md
#	collections/hve-core-all.collection.yml
#	plugins/hve-core-all/README.md
🔍 - Generated by Copilot
@agreaves-ms agreaves-ms merged commit 206d3a7 into microsoft:main Feb 19, 2026
19 checks passed
agreaves-ms added a commit that referenced this pull request Feb 19, 2026
#657)

# Pull Request

## Description

Add `dt-start-project.prompt.md` as the entry point for starting new
Design Thinking coaching projects.

- Create prompt file delegating to `dt-coach` agent
- Define input variables for project name and optional context
- Specify state directory initialization requirements
- Include frozen/fluid classification and Method 1 entry
- Add activation instruction for coaching kickoff

> [!NOTE]
> This PR depends on #656 (dt-coach agent) being merged first.

## Related Issue(s)

Closes #580

## Type of Change

Select all that apply:

**Code & Documentation:**

- [ ] Bug fix (non-breaking change fixing an issue)
- [x] New feature (non-breaking change adding functionality)
- [ ] Breaking change (fix or feature causing existing functionality to
change)
- [ ] Documentation update

**Infrastructure & Configuration:**

- [ ] GitHub Actions workflow
- [ ] Linting configuration (markdown, PowerShell, etc.)
- [ ] Security configuration
- [ ] DevContainer configuration
- [ ] Dependency update

**AI Artifacts:**

- [ ] Reviewed contribution with `prompt-builder` agent and addressed
all feedback
- [ ] Copilot instructions (`.github/instructions/*.instructions.md`)
- [x] Copilot prompt (`.github/prompts/*.prompt.md`)
- [ ] Copilot agent (`.github/agents/*.agent.md`)
- [ ] Copilot skill (`.github/skills/*/SKILL.md`)

**Other:**

- [ ] Script/automation (`.ps1`, `.sh`, `.py`)
- [ ] Other (please describe):

## Testing

<!-- Describe how you tested these changes -->

## Checklist

### Required Checks

- [x] Documentation is updated (if applicable)
- [x] Files follow existing naming conventions
- [x] Changes are backwards compatible (if applicable)
- [ ] Tests added for new functionality (if applicable)

### Required Automated Checks

The following validation commands must pass before merging:

- [ ] Markdown linting: `npm run lint:md`
- [ ] Spell checking: `npm run spell-check`
- [ ] Frontmatter validation: `npm run lint:frontmatter`
- [ ] Skill structure validation: `npm run validate:skills`
- [ ] Link validation: `npm run lint:md-links`
- [ ] PowerShell analysis: `npm run lint:ps`

## Security Considerations

- [x] This PR does not contain any sensitive or NDA information
- [x] Any new dependencies have been reviewed for security issues
- [x] Security-related scripts follow the principle of least privilege

## Additional Notes

🚀 Generated by Copilot

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Allen Greaves <allengreaves@microsoft.com>
WilliamBerryiii pushed a commit that referenced this pull request Feb 20, 2026
🤖 I have created a release *beep* *boop*
---


##
[3.0.0](hve-core-v2.3.10...hve-core-v3.0.0)
(2026-02-20)


### ⚠ BREAKING CHANGES

* **skills:** migrate PR reference generation to self-contained skill
([#669](#669))
* restructure RPI collection to HVE Core naming convention
([#668](#668))

### ✨ Features

* **agents:** add agile-coach agent
([#562](#562))
([de8d86c](de8d86c))
* **agents:** add DT coach agent with tiered instruction loading
([#656](#656))
([206d3a7](206d3a7))
* **agents:** add product manager advisor and UX/UI designer agents
([#627](#627))
([539eb8a](539eb8a))
* **agents:** add system architecture reviewer for design trade-offs and
ADR creation ([#626](#626))
([de5cfd6](de5cfd6))
* **build:** pin devcontainer image and align tool parity
([#704](#704))
([6258b1c](6258b1c))
* **design-thinking:** add manufacturing industry context template
([#682](#682))
([ce864bf](ce864bf))
* **instructions:** add DT coaching state protocol for session
persistence ([#654](#654))
([5a5be4e](5a5be4e))
* **instructions:** add dt-coaching-identity ambient instruction
([#642](#642))
([6209a0d](6209a0d))
* **instructions:** add dt-method-01-deep for advanced scope
conversation techniques
([#673](#673))
([cc92ef9](cc92ef9))
* **instructions:** add dt-method-03-deep for advanced input synthesis
techniques ([#676](#676))
([0079a4f](0079a4f))
* **instructions:** add dt-method-09-deep instructions for Method 9
advanced coaching
([#703](#703))
([150b2a6](150b2a6))
* **instructions:** add dt-method-sequencing ambient instruction
([#650](#650))
([e465b2f](e465b2f))
* **instructions:** add dt-quality-constraints and design-thinking
collection ([#645](#645))
([17002bd](17002bd))
* **instructions:** add DT-to-RPI handoff contract specification
([#679](#679))
([87f9962](87f9962))
* **instructions:** add energy industry context template
([#687](#687))
([41088d8](41088d8))
* **instructions:** add healthcare industry context template
([#686](#686))
([b2d5281](b2d5281))
* **instructions:** add Method 1 Scope Conversations coaching knowledge
([#651](#651))
([93e2d48](93e2d48))
* **instructions:** add Method 2 Design Research coaching knowledge
([#652](#652))
([30f7f3b](30f7f3b))
* **instructions:** add Method 3 Input Synthesis coaching knowledge
([#653](#653))
([1efdb7d](1efdb7d))
* **instructions:** add Method 7 High-Fidelity Prototypes coaching
instruction ([#666](#666))
([9233eab](9233eab))
* **instructions:** add pull request instructions for PR generation
workflow ([#706](#706))
([73d23eb](73d23eb))
* **instructions:** create DT curriculum content (9 modules)
([#690](#690))
([9f7378f](9f7378f)),
closes [#617](#617)
* **instructions:** create dt-method-02-deep.instructions.md
([#700](#700))
([4d4d0ca](4d4d0ca))
* **instructions:** create dt-method-06-lofi-prototypes.instructions.md
([#684](#684))
([4d5f757](4d5f757))
* **instructions:** create dt-method-07-deep.instructions.md
([#678](#678))
([d3ec70d](d3ec70d))
* **instructions:** Create dt-method-08-deep.instructions.md
([#683](#683))
([d9e1115](d9e1115))
* **instructions:** create dt-method-08-testing.instructions.md
([#681](#681))
([3008ad8](3008ad8))
* **instructions:** create dt-method-09-iteration.instructions.md
([#685](#685))
([9d7f4f5](9d7f4f5))
* **instructions:** create dt-rpi-research-context.instructions.md
([#689](#689))
([34c7b89](34c7b89))
* **instructions:** create manufacturing reference learning scenario
([#692](#692))
([1bd3994](1bd3994))
* **instructions:** Design Thinking Method 4 brainstorming instruction
file ([#664](#664))
([06f90b0](06f90b0))
* **prompts:** add DT start-project prompt for coaching initialization
([#657](#657))
([ce583d5](ce583d5))
* **prompts:** add dt-resume-coaching prompt for session recovery
([#665](#665))
([11b93cb](11b93cb))
* **prompts:** create dt-handoff-problem-space.prompt.md
([#688](#688))
([277963d](277963d))
* **scripts:** add collection-level maturity field with validation,
gating, and notices
([#697](#697))
([7b1c8e8](7b1c8e8))
* **scripts:** add per-violation CI annotations and colorized console
output ([#637](#637))
([bd7d512](bd7d512))
* **skills:** edit SKILL frontmatter schema, add CI validation, and
documentation ([#625](#625))
([0138a78](0138a78))
* **skills:** mandate unit testing and document language support
([#636](#636))
([9263617](9263617))
* **skills:** migrate PR reference generation to self-contained skill
([#669](#669))
([cf8805f](cf8805f))


### 🐛 Bug Fixes

* **collections:** migrate artifacts into collection-based
subdirectories
([#658](#658))
([dfa5261](dfa5261))
* **instructions:** optimize Phase 1 DT token budgets and close
[#564](https://github.com/microsoft/hve-core/issues/564)/[#565](https://github.com/microsoft/hve-core/issues/565)
gaps ([#675](#675))
([4f42f00](4f42f00))
* **scripts:** add CI annotations and step summary to copyright header
check ([#638](#638))
([5fa6328](5fa6328))
* **scripts:** add grouped link-lang console diagnostics and failure
summary ([#661](#661))
([4d6871f](4d6871f))
* **scripts:** add per-violation Write-Host and Write-CIAnnotation
output to Test-DependencyPinning
([#640](#640))
([9d3b71d](9d3b71d))
* **scripts:** align agent frontmatter schema with VS Code spec
([#469](#469))
([254d445](254d445))
* **scripts:** optimize PSScriptAnalyzer linting performance in WSL2
([#667](#667))
([f120b93](f120b93))
* **scripts:** stabilize YAML display key ordering in collection
manifest ([#701](#701))
([73c0d2c](73c0d2c))
* **scripts:** use text stubs for plugin links when symlinks unavailable
([#695](#695))
([d7650a3](d7650a3))
* **skills:** fix powershell test coverage in pr-reference skill
([#699](#699))
([408e6b7](408e6b7))


### 📚 Documentation

* **dt:** add Method 5 Concepts and Method 6 Lo-Fi Prototypes
instructions ([#693](#693))
([cfdcf11](cfdcf11))
* **hve-guide:** add role-based guides and project lifecycle
documentation ([#663](#663))
([17a85da](17a85da))


### ♻️ Refactoring

* restructure RPI collection to HVE Core naming convention
([#668](#668))
([120dde0](120dde0))
* **scripts:** consolidate duplicate logging into shared SecurityHelpers
module ([#655](#655))
([627a877](627a877))
* **scripts:** use shared SecurityHelpers and CIHelpers modules in
security scripts
([#705](#705))
([3a0baa7](3a0baa7))


### 🔧 Maintenance

* **deps-dev:** bump markdownlint-cli2 from 0.20.0 to 0.21.0 in the
npm-dependencies group
([#609](#609))
([1486dd7](1486dd7))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

Co-authored-by: hve-core-release-please[bot] <254602402+hve-core-release-please[bot]@users.noreply.github.com>
@chaosdinosaur chaosdinosaur deleted the feat/579-dt-coach-agent branch February 24, 2026 18:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

5 participants