I Had Already Built Three Agentic Loops Without Naming Them

Description and use

The author formalized three nested feedback loops—execution plan, milestones, and TDD+architecture—to enable an AI coding agent to autonomously implement features while ensuring progress, architectural compliance, and final acceptance.

Problem

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?

Outcome

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.

Workflow

• 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.

Evidence

The outermost layer is the execution plan.

Source

Inside the milestones is the smallest and most active layer.

Source

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

Source