I fixed my AI reviewer. Then I kept solving the wrong problem

I've been building an AI-assisted editorial pipeline for technical writing. Notion cards become markdown drafts in the repo, pass through review, then sync to dev.to.

Last month I shipped a post about the first big fix to my editor-critique reviewer skill: The AI reviewer scored 23/25 and missed the point. The problem was sequence. A score-first pass treated a polished rubric as the first lens and produced QA feedback when I needed editorial feedback. Reordering the skill so analysis precedes scoring fixed that.

I assumed the next improvements would come from rubric tuning. Longer prompts. Another scoring dimension. Sharper checklists.

That assumption was half right. The rubric still matters. But every useful fix after the baseline shared a different shape.

The pattern I kept missing

I've been building an AI-assisted editorial pipeline for technical writing. Notion cards become markdown drafts in the repo, pass through review, then sync to dev.to.

I assumed the next improvements would come from rubric tuning. Longer prompts. Another scoring dimension. Sharper checklists.

That assumption was half right. The rubric still matters. But every useful fix after the baseline shared a different shape.

The pattern I kept missing

I fixed my AI reviewer. Then I kept solving the wrong problem

I fixed my AI reviewer. Then I kept solving the wrong problem

Related reading

The AI reviewer scored 23/25 and missed the point

One good example beat every AI writing rule I wrote

I Reviewed 200+ AI-Generated PRs. Here's the 4-Round Protocol I Use Now.

AI wrote my bug. I shipped it anyway. Here’s what I learned.

I Let 24 Famous Engineers Review My Methodology. Here's What Happened.

Why AI Still Can't Write Well and Which Half of That Problem Is Actually Yours

Related reading

The AI reviewer scored 23/25 and missed the point

One good example beat every AI writing rule I wrote

I Reviewed 200+ AI-Generated PRs. Here's the 4-Round Protocol I Use Now.

AI wrote my bug. I shipped it anyway. Here’s what I learned.

I Let 24 Famous Engineers Review My Methodology. Here's What Happened.

Why AI Still Can't Write Well and Which Half of That Problem Is Actually Yours