scoring logic v2: the score finally earns the number
scoring logic v2: the score finally earns the number
a bad score is annoying. a fake-good score is worse.
that was the problem with the old voice score. you could paste a draft with obvious ai writing patterns, five things that still needed fixing, and a voice that did not really match the profile. somehow the number could still sit around 70 or 80. not because the writing earned it. because the scoring logic was too forgiving in the wrong places.
it made the product feel confused. the issue cards were saying "fix this." the score was saying "mostly fine." users were right to ask what was going on.
what changed
scoring logic v2 is a rebuild of the premise. the score does not start at a polite middle number and drift up or down. it earns points from evidence in the draft.
get started for $1 — create your account and scan your first draft in minutes.
get started for $1 →
how does the score earn its points?
each bucket answers a different question. does this sound like the profile? did the draft pick up the patterns we know to watch? how much repair is still waiting? and, after all that, is the writing doing its job?
the buckets are separate on purpose. a draft can be strong but off-profile. it can sound like you while carrying too much ai-shaped structure. one number should not hide those differences.
what does a lower score mean?
a lower score means the draft has visible work left. it does not mean the idea is bad, or that every sentence needs a rewrite. the issue cards are the useful part: they show which evidence pulled the number down.
that changes the editing loop. you can fix the three lines creating most of the drift, rescan, and see whether the number moved for the right reason. the score becomes a receipt for the edit, not a mood assigned by a model.
what should you do with a high score?
read the draft anyway. a high score says the writing is close to the profile and relatively clean. it does not prove the claim is true, the argument is useful, or the reader will care.
the practical rule is simple: use the score to decide where to look, then use your judgment to decide whether the piece deserves to ship. the product can measure drift. it cannot replace taste.
that is the point of v2. the number is smaller than the evidence underneath it.
writes about brand voice, ai writing patterns, and the craft of sounding like yourself. built hold your voice after watching his own voice flatten across six months of heavy ai drafts.
co-written with ai as sidekick. shashank drafted the observations; the ai pressure-tested the structural claims. if something reads too smooth, that's the ai's fault.