v1 to v2: what changed in how your voice profile gets built
v1 to v2: what changed in how your voice profile gets built
for the past month, hold your voice asked you to describe how you write.
onboarding was a flashcard quiz. you picked between apple and nike for "voice style." between slack and mckinsey for "tone." between brené brown and goldman sachs for how you build an argument. ten questions, ten brand-flavored multiple-choice answers. our ai turned them into ten voice keywords. that was your voice profile.
it worked. it just wasn't yours.
the gap i missed for too long
six weeks ago i was using my own product on a real draft. the rewrite came back sounding fine. competent. wrong.
i dug into the prompt. it was using the keywords i'd picked during onboarding. concise, direct, specific. what those words mean to me, what they sound like when i actually write, none of that was in there. the model had labels. it didn't have a voice.
here's the analogy that finally cracked it for me. you tell a chef "i like food that's bold and rustic and seasonal." they cook you something. it's bold and rustic and seasonal. and it's nothing like what you actually cook in your own kitchen.
what v2 reads instead
v2 is built around one switch. instead of asking what kind of writer you are, we read what you've actually written.
get started for $1 — create your account and scan your first draft in minutes.
get started for $1 →
the profile now looks for repeatable evidence: sentence length, openings, transitions, preferred levels of detail, words you reach for, and the places where you usually take a position. those signals are useful because they came from your work, not from a personality quiz.
what happens when the samples disagree?
the profile should not flatten disagreement into a fake average. a sales email and a personal essay can have different shapes while still belonging to the same writer.
v2 keeps the stable traits and treats format as context. the question is not whether every piece uses the same rhythm. it is whether the change makes sense for the job the piece is doing.
what does v2 change in a rewrite?
the rewrite gets examples instead of labels. “be concise” is a direction. a sample that shows how you compress an idea is evidence.
that difference matters when the model is making a choice. it can now compare a proposed sentence with the way you actually make that choice in your own writing.
what should you do when the profile feels wrong?
do not add more adjectives. add better evidence. remove samples that no longer represent your work, add a recent piece you would sign today, and review the changes the profile is making.
a voice profile is not a permanent identity card. it is a working model of the writing you want to preserve.
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.