I Had Already Built Three Agentic Loops Without Naming Them

说明与用途

作者通过建立执行计划、里程碑和 TDD+架构三层嵌套反馈循环，使 AI 代码生成器能够自主实现功能，同时确保进度、架构合规和最终验收。

问题

How to give an AI coding agent enough autonomy to implement a feature while ensuring it stays on target, respects architecture, and delivers observable progress?

结果

By structuring the workflow into three nested loops, the author achieved higher agent autonomy, reduced manual checkpoints, and ensured that each stage of development—planning, milestone completion, and behavior/architecture compliance—was independently validated.

工作流

• Define an execution plan that includes purpose, context, desired behavior, constraints, milestones, validation strategy, and acceptance criteria.
• The agent executes the plan, updates it as it discovers new information, and continues until the final acceptance criteria are met.
• Within the plan, the agent follows milestones, each with its own scope, validation commands, expected result, and acceptance criteria.
• At each milestone, the agent runs TDD cycles: write failing test, implement minimal code, refactor if needed, and repeat until tests pass.
• During TDD, architectural tests (e.g., HexagonalArchTest) run to enforce design boundaries; failures trigger design corrections before proceeding.
• After a few TDD cycles, the agent validates the feature through its public path to prevent drift into implementation details.
• The agent continues until all loops report success; the author then reviews the pull request for final approval.

证据

The outermost layer is the execution plan.

来源

Inside the milestones is the smallest and most active layer.

来源

The agent does not become more autonomous because I stopped caring about the process.

来源