One Loop, One Oracle
A reusable method for agentic software development: a human defines the desired outcomes, agents work through the tasks, and a merge gate checks the finished functionality against the running product. A fixed task list, protected acceptance scenarios and regular regression tests guide development. The process transfers across products and models.
Introducing the Coordinator
Three product owner agents answer for their own assignments in parallel. A coordinator settles the conflicts they cannot settle themselves and merges reviewed changes. Behind every completion report he demands independent evidence. This covers what each role may decide, which model sits on which role, and how the Codex sessions reach each other. Errors in tests and reviews led to changes in the development process.
The Limits of Human Sign-Off in Agentic Software Development
A human sign-off in an agentic SDLC certifies a fixed state of the work against criteria defined in advance. It does not cover the agent run itself. My experience and five papers from spring and summer 2026 point to cognitive overload. Placing a human in the loop can create the appearance of safety and participation.