HumanLayer co-founder Kyle Mistele argues that enormous unattended pull requests are a poor fit for many teams. He uses control theory to describe an alternative: measure the current state, compare it with a desired state, choose an incremental action and measure again. Deterministic checks can supply a reliable sensor while an agent handles a narrowly scoped change.
A code-migration example combines AST-grep checks with a recorded baseline, hand-written migration patterns and a skill for producing consistent changes. Existing CI detects regressions, and the controller selects manageable work instead of asking the model to transform the entire codebase at once.
Human review becomes feedback for subsequent iterations. Limiting each loop to one open pull request prevents a backlog of unreviewed changes; separate bounded contexts can support larger programs of work. Mistele presents this as a practical engineering approach, not a guarantee that any autonomous coding loop will be safe.
Watch on YouTube
