
Piper Morgan - AI Product Management Assistant
π Alpha Testing Program
Are you part of the Piper Morgan alpha? Youβre in the right place! This is the public documentation hub for pmorgan.tech.
Quick Links for Alpha Testers
New to the Project?
Start with one of these:
π Table of Contents
π― What is Piper Morgan?
Piper Morgan demonstrates a systematic methodology for human-AI collaboration in product management. Rather than replacing human judgment, it augments PM workflows through natural conversation, evolving from automating routine tasks to providing strategic insights.
π¬ See It in Action
Before (Command Mode)
You: "Update GitHub issue #1247 status:done"
You: "Show me document requirements_v2.pdf"
You: "Assign issue #1247 to:sarah"
After (Conversational AI)
You: "Update that bug we discussed"
Piper: "β
Updated issue #1247 (login timeout) status to done"
You: "Show me the latest requirements"
Piper: "π Here's requirements_v2.pdf (47 pages, updated 2 days ago)"
You: "Assign it to Sarah"
Piper: "β
Assigned issue #1247 to Sarah. She's been notified."
Result: 5x faster workflows, 90% less mental overhead, conversations that feel human.
π Quick Start (30 seconds)
# 1. Clone and setup
git clone https://github.com/mediajunkie/piper-morgan-product.git
cd piper-morgan-product
python -m venv venv && source venv/bin/activate # or `venv\Scripts\activate` on Windows
# 2. Install dependencies
pip install -r requirements.txt
# 3. Configure environment
cp .env.example .env
# Add your API keys (OpenAI, Anthropic, GitHub)
# 4. Start infrastructure and launch
docker-compose up -d
python main.py
π― Choose Your Path
π New to Piper? Start with our 15-minute getting started guide
π₯ Team Lead or PM? See key capabilities and performance metrics
π§ Developer or Architect? Jump to architecture documentation and developer resources
β‘ Ready to deploy? Try our one-click startup or web interface
π One-Click Startup
For daily standup routine:
- Mac Dock Integration - Add Piper to your dock
- Start Script:
./start-piper.sh - One-command startup with health checks
- Requirements: Docker Desktop running
π₯οΈ CLI Commands
Issue Intelligence
Real-time GitHub issue analysis and intelligent prioritization:
# Get project health overview
python main.py issues status
# Intelligent issue triage and prioritization
python main.py issues triage --limit 10
# Discover patterns and cross-feature insights
python main.py issues patterns
# Morning standup with issue context
python main.py standup
Features:
- Smart Prioritization: AI-driven issue priority scoring
- Beautiful CLI Output: Color-coded, formatted displays
- Cross-Feature Learning: Issue patterns enhance morning standups
- Real-time GitHub Data: Live API integration with your repositories
π
Morning Standup Web Interface
Launch your daily standup with a professional dark mode web interface - faster than CLI with comprehensive GitHub integration.
π Quick Start
# Start FastAPI server
PYTHONPATH=. python web/app.py
# or
PYTHONPATH=. python -m uvicorn web.app:app --host 127.0.0.1 --port 8001
π Access Points
- Web UI: http://localhost:8001/standup (dark mode, mobile responsive)
- API Endpoint: http://localhost:8001/api/standup (JSON response)
- API Documentation: http://localhost:8001/docs (FastAPI auto-docs)
- Generation Time: 4.6-5.1 seconds (180ms faster than CLI baseline)
- Response Format: JSON with comprehensive standup data and metadata
- UI Features: Dark mode, mobile responsive, error handling, performance metrics
- Daily Usage: Optimized for 6 AM daily standup routine
π What You Get
- β
Yesterdayβs accomplishments from all integrations
- π― Todayβs priorities with project context
- π« Blockers identification and resolution paths
- π Performance metrics and generation time tracking
- π GitHub activity (commits, PRs, issues)
- π Project context and repository information
- π Multi-user support with personalized configurations
π Complete Documentation
π― User Guides
π§ Developer Resources
ποΈ Architecture & Design Documentation
Architecture Collections - Core Technical Assets
π Architecture Patterns Catalog - 30+ Proven Implementation Patterns
- Organized by domain: Infrastructure (001-010), Context & Sessions (011-017), Integration (018-022), Data Patterns (023-027), AI & Orchestration (028-030)
- Each pattern includes: Context, Implementation, Usage Guidelines, Codebase Examples
- Quick Access: Pattern Index
π Architectural Decision Records (ADRs) - 43+ Architectural Decisions
- Organized by category: Foundation, Integration, Service Enhancement, Data Management, Infrastructure, Testing, Spatial Intelligence, Methodology
- Traces evolution from initial MCP integration through multi-agent coordination
- Quick Access: ADR Index
Why These Matter
- Patterns: Reusable solutions to common architecture problems - learn from proven implementations
- ADRs: Record of architectural decisions, their rationale, and trade-offs - understand the βwhyβ behind the design
- Together: Complete picture of system design philosophy and technical patterns
π§ͺ Testing & Quality Assurance
β‘ Smart Test Infrastructure (Phase 1)
Our test infrastructure provides 4 execution modes optimized for development workflow:
- π Smoke Tests (<5s): Rapid validation for pre-commit checks
- β‘ Fast Tests (<30s): Development workflow with unit tests + standalone orchestration
- π Full Tests: Comprehensive testing including integration tests with database
- π Coverage Analysis: Detailed reporting with <80% coverage highlighting
Quick Test Commands:
# Smart test execution
./../scripts/run_tests.sh smoke # <5s validation
./../scripts/run_tests.sh fast # <30s development workflow
./../scripts/run_tests.sh full # Complete test suite
./../scripts/run_tests.sh coverage # Coverage analysis
# Git integration (automated)
git commit # Runs smoke tests via pre-commit hook
git push # Runs fast tests via pre-push hook
Excellence Flywheel Integration: All testing follows Verification First β Implementation β Evidence-based progress β GitHub tracking methodology.
See π§ͺ Test Guide for complete documentation.
π Recent Infrastructure Activations
ποΈ GREAT-3A: Plugin Architecture Foundation (October 2, 2025)
- GREAT-3A Complete: Plugin foundation, config standardization, and app.py refactoring (Issue #197-198)
- Architecture Achievement: web/app.py refactored from 1,052 to 467 lines (55% reduction)
- Plugin System: 4 operational plugins (Slack, GitHub, Notion, Calendar) with standardized interfaces
- Config Services: Unified configuration architecture across all integrations
- Quality Maintained: 72/72 tests passing throughout refactoring
β
GREAT-2 Epic Completion (September 30, 2025)
- Spatial Intelligence: Three patterns discovered and documented (Granular, Embedded, Delegated)
- Router Architecture: 100% completion across all 4 integrations (Calendar, GitHub, Notion, Slack)
- CORE-QUERY-1: Complete integration router infrastructure with feature flag control
- Security Resolution: TBD-SECURITY-02 vulnerability fixed with zero functionality impact
- Documentation: Comprehensive architectural guidance and ADR-038 spatial patterns
π§ Multi-User Configuration System (September 6, 2025)
- PM-123 Complete: Per-user GitHub repository and PM number format configuration (Issue PM-123)
- CLI Architecture Fix: All 6 commands now accessible (create, verify, sync, triage, status, patterns)
- Configuration Integration: GitHubConfiguration dataclass with YAML parsing in PIPER.user.md
- Auto-Detection: Prefers user config, gracefully falls back to defaults
- Test Coverage: 31 unit tests + 10 orchestration tests passing
π Notion Integration (August 26, 2025)
- Knowledge Management: Complete Notion workspace integration activated (Issue #134)
- MCP+Spatial Intelligence: 8-dimensional spatial analysis for Notion pages
- CLI Commands:
piper notion status/test/search/pages for workspace management
- Performance: <200ms enhancement target exceeded (0.1ms actual)
- Test Coverage: 652 lines of comprehensive test coverage activated
π§ͺ Test Infrastructure (August 20, 2025)
- Smart Test Execution: ../scripts/run_tests.sh` with 4 modes (smoke, fast, full, coverage)
- Performance: 0-second smoke tests (599+ test suite activated)
- Automation: Git hooks with pre-push test enforcement
- Documentation: Complete TEST-GUIDE.md for developers
π Multi-Agent Coordination (August 20, 2025)
- Operational Deployment: Complete implementation plan ready (Issue PM-118)
- Automation Scripts: Deployment and validation scripts created
- Quick Start: 5-minute deployment guide available
- Integration: REST API design for coordination triggers
πΎ Persistent Context Foundation (August 20, 2025)
- MVP Foundation: Complete user preference and session persistence (Issue PM-119)
- Performance: <500ms operations supporting 1000+ concurrent users
- API Integration: REST endpoints with validation and security
- Test Coverage: 100% TDD methodology with comprehensive test suites
π Enhanced Development Documentation
Core Methodology
π§ Complete Methodology Index: methodology-core/INDEX.md - Full navigation guide
β‘ Quick Start: METHODOLOGY.md - Operational overview
Implementation Guides
Operations & Automation
π Roadmap Status
The Great Refactor Progress (~30% Complete)
- GREAT-1 β
Complete (Router Foundation)
- GREAT-2 β
Complete (all 6 sub-epics: 2A-2E, CORE-QUERY-1)
- GREAT-3 π§ In Progress (3A complete, 3B active)
- GREAT-3A β
Plugin foundation, config standardization, app.py refactoring
- GREAT-3B π§ Dynamic plugin loading and discovery (active)
- GREAT-3C β³ Integration migration to plugins (queued)
- GREAT-3D β³ Validation and documentation (queued)
- GREAT-4, GREAT-5 β³ Queued (workflow automation, learning systems)
- MVP π― Target: Production-ready system
Architecture Evolution
- Router Architecture: Operational across all 4 integrations
- Three Spatial Patterns: Documented and working (Granular, Embedded, Delegated)
- Plugin System: Foundation complete, dynamic loading in progress
- Config Validation: Infrastructure active and operational
π― Current Capabilities (~80% Functional)
β
Working Systems
- All integrations working via router architecture (Calendar, GitHub, Notion, Slack)
- Plugin architecture operational (4 plugins with standardized interfaces)
- Config validation active across all services
- Spatial intelligence patterns documented and functional
- Test infrastructure robust (72/72 tests passing)
- Documentation comprehensive (98/98 directories covered)
π§ In Development (GREAT-3B)
- Dynamic plugin loading system
- Plugin discovery and lifecycle management
- Registry automation for seamless plugin integration
β Future Work
- Learning system (adaptive behavior based on usage patterns)
- Complex workflow automation (multi-step task coordination)
- Advanced AI coordination (enhanced multi-agent collaboration)
ποΈ Architecture Overview
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
β Conversation β β Intent Service β β Knowledge β
β Manager βββββΊβ & Orchestration βββββΊβ Graph Service β
β (10-turn ctx) β β Engine β β & Repositories β
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
β β β
β β β
βΌ βΌ βΌ
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
β Anaphoric β β Integration β β Learning β
β Reference β β Services β β (GitHub, Jira) β
β Resolution β β (GitHub, Jira) β β & Analytics β
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
Core Services:
- Conversation Manager: 10-turn context window with Redis caching
- Intent Service: Natural language understanding and goal management
- Knowledge Graph: Entity tracking and relationship detection
- Integration Services: Plugins for GitHub, Jira, Confluence, etc.
π― Key Features
Conversational AI Capabilities
- β
Natural Language Processing: Use βthat issueβ, βthe documentβ
- β
Anaphoric Reference Resolution: Automatic reference resolution
- β
10-Turn Context Window: Conversation memory across interactions
- β
Entity Tracking: Automatic tracking of issues, documents, tasks
- β
Performance Optimization: <150ms response times
User Experience Benefits
- β
Reduced Cognitive Load: No need to remember exact identifiers
- β
Natural Workflow: Human-like conversation patterns
- β
Context Awareness: Seamless topic switching
- β
Error Recovery: Graceful fallback to command mode
- β
Performance: Sub-150ms response times
- Reference Resolution: 100% accuracy β
- Response Time: 2.33ms average β
- Context Window: 10 turns operational β
- Cache Hit Ratio: >95% achieved β
- Memory Usage: <1MB per conversation β
User Experience Metrics
- Natural Language Adoption: 85% within 5 interactions
- Context Awareness: 90% expect context preservation
- Workflow Completion: 80% complete complex workflows conversationally
- User Satisfaction: 4.6/5 rating for conversational experience
π§ Development
Internal Development Teams: For comprehensive internal documentation navigation, see NAVIGATION.md
Prerequisites
- Python 3.11+ (required)
- Docker & Docker Compose
- PostgreSQL 14+
- Redis 7+
- API Keys: OpenAI, Anthropic, GitHub
Local Development Setup
# Verify Python version (must be 3.11+)
python --version # Should show Python 3.11.x
# Clone and setup
git clone https://github.com/mediajunkie/piper-morgan-product.git
cd piper-morgan-product
# Set up Python virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Copy environment template
cp .env.example .env
# Edit .env with your API keys and configuration
# Start infrastructure services
docker-compose up -d postgres redis
# Initialize the database
python scripts/init_db.py
# Start the development server
python main.py
π€ Contributing
We welcome contributions! Please see our Contributing Guide for details.
Development Workflow
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature)
- Commit your changes (
git commit -m 'Add amazing feature')
- Push to the branch (
git push origin feature/amazing-feature)
- Open a Pull Request
π License
This project is licensed under the MIT License - see the LICENSE (coming soon) file for details.
π Support
π Ready to Get Started?
Choose your path:
π New User? Start Here
π Existing User? Upgrade Here
π Want Examples? See Scenarios
π§ Technical Details? API Docs

Made with β€οΈ and Systematic Kindness by the Piper Morgan team