The original title is: "Turn one giant AI-generated pull request to a reviewable stack"

Short summary

GitHub introduces a workflow for decomposing large AI-generated pull requests into clean, ordered stacked PRs that are actually reviewable. The approach teaches coding agents to break work into logical increments rather than producing one monolithic diff. This addresses a growing pain point as AI coding assistants generate increasingly large changesets that overwhelm human reviewers.

• •GitHub proposes stacked pull requests as a solution to unreviewable AI-generated PRs
• •Coding agents can be guided to decompose work into ordered, reviewable increments
• •Targets the growing problem of oversized diffs from AI coding assistants

Generated with AI, which can make mistakes.