The proposal: remove editors before proving agent reliability
The long-term vision called for fewer separate editing and review stages. To move toward that vision, the team proposed keeping editors out of the formal workflow in the initial few months itself, moving editors to more of an agent QA role, and banked on the agent being really good.

My stance: keep expert review in the MVP
I pushed back on doing that in the MVP and this is a capability I’d defend the hardest.

The problem: authors need support; agents need ground truth
Authors were making decisions that specialists used to handle, some on standards they’d never had to interpret. Removing editors would shorten the workflow, but it would also remove the support authors needed. A suggestion appearing in the interface alone, no matter how strong or good, did not give the author the information to judge whether it is right. The product alone could not close that knowledge gap. Moreover, for the system, capturing editor judgment was the first reliable ground truth we had, which meant we could measure where the agent and editors agreed and where they didn’t. That turned the phased approach from a leap of faith into a measurable one: as agreement on a category rose, editors stepped back from it, and stayed in the loop where the agent was still unreliable.

The decision: phase the handoff and explain recurring disagreements
I proposed a phased approach. Authors write and review first. Editors then review separately, approving or overriding findings and recording why. Those decisions became the context layer behind every finding. But I didn’t rally to surface editor reasoning on every finding. When an author and an editor have historically made the same call, there’s nothing to teach, and extra explanation is just noise. I reserved it for the moments they repeatedly disagree: “Editors had feedback on your last 2 dismissals of this type,” with the standard and how editors ruled on similar cases. The addition to the interface was a small interaction with a larger purpose: it made expert judgment visible at the point where responsibility was moving to the author and providing authors help only where they needed it, at the moment they were about to repeat a mistake. It provided a basis for confidence beyond simply trusting the agent, or worse, guessing what their response should be, which is not reliable ground truth for our systems to improve upon.

AI’s role: turn past overrides into timely author guidance
The AI looks across an author’s history for dismissals that editors later overrode. A repeated conflict signals a knowledge gap, not a preference. When the author is about to make that call again, the AI joins the finding to the relevant standard and past editor rationale, then writes a short explanation tied to their passage. For subjective findings like tone and flow, I framed it as “how editors usually approach this,” not “you’re wrong.”