AI Development Workflow
tfplan2md is developed using a multi-agent AI workflow where specialized agents handle different phases of the development lifecycle.
Overview
This project uses an agent-based workflow for feature development, inspired by best practices from GitHub Copilot agents and modern software engineering principles. Each agent is a specialized AI assistant with a clear responsibility in the development process.
The workflow is coordinated by a human Maintainer who manages handoffs between agents and provides clarifications as needed. Agents produce artifacts as markdown files in the repository, creating a traceable development history.
Clear Responsibilities
Each agent has a single, well-defined role in the workflow
Traceable Artifacts
All decisions and changes are documented in markdown files
Consistent Process
Standardized workflow ensures quality and completeness
AI-Powered
Leverages GitHub Copilot's multi-model capabilities
Workflow Diagram
The diagram below shows the complete agent workflow from requirements to release. Each agent produces artifacts that are consumed by the next agent in the sequence.
Agents produce and consume artifacts. Solid arrows show artifact creation and consumption. Dashed arrows indicate rework/feedback loops.
Key Agents
Requirements Engineer
Gathers and clarifies requirements for new features
Issue Analyst
Investigates bugs and technical issues
Architect
Designs solutions and documents decisions
Quality Engineer
Defines test plans and acceptance criteria
Developer
Implements features and tests
Technical Writer
Updates and maintains documentation
Code Reviewer
Reviews code quality and standards
UAT Tester
Validates user-facing features
Release Manager
Prepares and executes releases
Retrospective
Identifies improvement opportunities
Workflow Engineer
Improves the workflow itself
Web Designer
Maintains the project website
How It Works
Entry Point
The Maintainer identifies a need (new feature, bug fix, or workflow improvement) and starts with the appropriate entry agent.
Agent Collaboration
Each agent produces artifacts (markdown documents) that serve as inputs for the next agent in the workflow.
Traceability
All decisions, requirements, and changes are documented in versioned artifact files in the repository.
Quality Gates
Code Reviewer and UAT Tester validate changes before Release Manager creates the pull request.
Continuous Improvement
Retrospective analyzes the process and provides feedback to the Workflow Engineer for improvements.
Dual-Mode Execution
The workflow supports both local (VS Code) and cloud (GitHub) execution modes, enabling both interactive development and automated workflows.
🖥️ Local Mode (VS Code)
- Interactive development with Maintainer
- Design decisions and debugging
- Full tool access (edit, execute, preview)
- Best for complex tasks requiring guidance
☁️ Cloud Mode (GitHub)
- Automated execution from GitHub issues
- Well-scoped batch updates
- Creates pull requests autonomously
- Best for routine, well-defined tasks
Learn More
This page provides a high-level overview of the AI workflow. For complete details including artifact formats, handoff criteria, and best practices, see the full documentation.