Coding-agents

Today's pull request is built around a diff. You review what changed, not how it came to be. With coding agents, that model is starting to leak: a clean diff can hide a messy session, skipped constraints, or a plan that was wrong for three iterations before it was right. This post explores a new kind of PR — one where the artifact under review is the agent session itself: the prompts, the tool calls, the rejected paths, the plan, and the human's choices along the way. It compares the idea to existing practices like AI review bots, stacked diffs, build provenance, and "session provenance", and argues that making the session the primary review surface is genuinely new — and probably inevitable.

Reid Hoffman makes a specific point that cuts through the noise about AI "replacing developers": the job does not disappear, but the center of gravity shifts. The software engineer moves away from being primarily a person who types code, and toward being a person who manages multiple coding agents. He compares it to the difference between playing an instrument and conducting an orchestra—the output still becomes music, but the work becomes coordination, direction, and quality control rather than manual performance. This post breaks down his framing, the conductor metaphor, what it means for engineering careers, and how to build the reflex before the shift accelerates.