Skip to content
Developer Toolkit

Standard Workflow Patterns

AI coding assistants are not just code generators; they are partners in the entire development lifecycle. To get the most out of this partnership, it helps to follow structured workflows that play to the AI’s strengths. While there are many ways to work with an AI, a few core patterns have proven to be consistently effective across a wide range of tasks, from building new features to refactoring legacy code.

This section will introduce these standard workflows, providing a repeatable blueprint for success.

The Core AI-Assisted Workflow: Plan, Execute, Verify

Section titled “The Core AI-Assisted Workflow: Plan, Execute, Verify”

The most successful and reliable pattern for working with an AI assistant on any non-trivial task can be broken down into three phases:

1. Plan Phase: The Architect

In this phase, you act as the architect and the AI acts as your research assistant. Your goal is to explore the problem, understand the codebase, and create a detailed, step-by-step implementation plan. This is a low-risk, high-leverage activity that sets the stage for success.

2. Execute Phase: The Supervisor

Here, your role shifts to that of a supervisor. You delegate the implementation of the plan, one task at a time, to the AI. You review the code it produces, provide feedback, and ensure the implementation stays on track.

3. Verify Phase: The Quality Engineer

Finally, you become the quality engineer. You work with the AI to write tests, debug issues, and verify that the implementation meets all requirements. This ensures that the speed gained from AI assistance doesn’t come at the cost of quality.

This “Plan, Execute, Verify” cycle is the foundation for many of the specific development patterns discussed in the following guides, including the core “PRD → Plan → Todo” methodology.

Why This Pattern Works

Section titled “Why This Pattern Works”
  • Reduces Risk: By starting with a thorough planning phase in a “read-only” mode, you can catch potential issues and refine your approach before any code is written.
  • Improves Quality: The iterative nature of the execution phase and the dedicated verification phase ensure that the final code is well-tested and robust.
  • Maximizes Efficiency: It allows you and the AI to focus on what you each do best. You provide the high-level strategy and domain knowledge, while the AI handles the detailed, often tedious, work of implementation and testing.
  • Keeps You in Control: At every step, you are guiding the process. The AI is a powerful tool, but you are always the one making the final decisions.

The following guides will dive deeper into specific implementations of this pattern, from Test-Driven Development to Domain-Driven Design, showing you how to adapt this core workflow to your specific needs and methodologies.