Essay
Brand Voice Is Language + Cognition
Most brand-voice guides capture only the words, which is why AI writing built on them still sounds generic. This is how I rebuilt ours from the transcripts of three people on our team, and what I found underneath the language.
For the umpteenth time, my producer, our team's heaviest hitter for writing, came to me with a voice problem. My plate was full and I'd been ignoring it.
"Elizabeth, this blog post is not great."
He was right. I'd stripped out the em dashes and words like "quietly," and it still sounded like AI, and worse, it didn't sound like us. I told him I'd look at it later, already planning to push it to next week. Then I opened an email we'd sent that morning, and the subject line was a cardboard cutout of our brand, flimsy and two-dimensional. That was the moment I stopped pushing it to next week.
I knew what I'd been doing, and it wasn't working. I'd been telling our AI what not to do: no em dashes, no rhetorical questions to open, none of that word or that phrase or that verbal tic. Every time I closed one gap it opened another. I told it to stop hedging and it started over-claiming. I told it to stop over-claiming and it hedged. Maddening.
The subject line was a cardboard cutout of our brand, flimsy and two-dimensional.
Banning words never made it sound like us
I realized that a voice, for a real person, isn't a list of words you permit and forbid. It's a way of thinking, and the words are where you can see it happen.
That's why the style sheet kept failing me. It captured the visible part of something that mostly isn't visible. So I stopped writing rules and went to the source.
We had hours of webinar footage of our founding team, which meant I didn't need Claude to guess what our voice was. I had it on tape. I pulled the transcripts of three people in particular.
One of them sees the whole board and can sell a vision. One knows the research all the way down and won't let you approximate it. One is a coach, warm and practical, always pulling it back to what a teacher does on a Monday.
The mission underneath was the same, but each of them had a distinct way of thinking and speaking. I wanted the blend. One person's voice is just a copy, and my hunch was that braiding three complementary ways of thinking would produce something none of them would have written alone.
Different voices shared the same moves
Two things came back after I had Claude run the analysis, and I didn't expect either one.
The first was how much depth was there. Each person didn't have one way of answering a question; they each had several, and which one they reached for depended on the kind of question: one answer for a factual gap, another for a disagreement about values, another for a half-formed idea that needed room.
A voice guide takes a person and flattens them into three adjectives and a list of approved words.
The second thing was structural. All three people spoke differently, but they shared a few moves, and the clearest one was about honesty.
Generic AI hedges as a reflex, softening sentences while over-claiming in the same breath. None of the three did that. They were precise about the limits of what they knew, and they would each open the same honest way, marking what they knew against what they believed: we know comprehension matters for reading, and we believe social studies gives students the knowledge that unlocks it.
A voice guide takes a person and flattens them into three adjectives and a list of approved words.
Then each of them turned that limit somewhere different. One asked what question we'd need to answer to know if it was true. One reframed it as a chance to learn. One pointed past it to a bigger possibility.
Same claim, same honesty about where it stopped, and each of them turned the stopping point into an invitation.
The signal was in how they thought
That's when it stopped being about language for me. How a person handles the edge of what they know happens before the sentence does. The words are where it surfaces.
So I asked Claude to go down another level, past the language to what was distinct about how each of these people thinks.
I hadn't expected much from this layer. All three spoke from experience in the work, not in generalities. They all named the constraint before the solution: "here's where implementation fails" before "here's how you teach this curriculum," and "I'm not going to sugar coat it, doing it this way is harder" before "we can get every kid writing with purpose." They were making the same moves in the same places, though none of them had ever spoken to each other about how they speak.
How a person handles the edge of what they know happens before the sentence does. The words are where it surfaces.
I could ask for stronger verbs all day. I could tell the model to stop writing in threes. None of it made our writing better or truer to our brand, because it was missing half the puzzle.
And, of course, just feeding it words and rules didn't work. That's not how any of us learn language. We learn language from the people around us, and we pick up how they think in the same motion that we pick up how they speak, and both keep evolving as our lives and our relationships change. Your voice is never only yours, and it's never finished. It's a blend you've been assembling without noticing since before you could read.
That's not how any of us learn language. We learn it from the people around us.
Same words, different order
I had Claude write the same blog post two ways, once with our language rules alone and once with the language and the cognition patterns together.
The language-only version opened like this:
A first grader stares at the blank page. She learned something today. She talked about it, listened to her classmates, built an idea. But the page stays blank. This is easy to read as a writing problem. It usually isn't.
That already reads like a person wrote it. Someone is in the room, the sentences are plain, the abstraction is gone. A year ago I would have called it done. But look at what it does. It hands you the right answer, that it usually isn't a writing problem, and keeps moving. It never sits with you in the wrong answer first.
The version with cognition added opened almost identically:
A first grader stares at the blank page. Her teacher asked her to write about what she learned, and she has learned plenty. She listened, she talked, she built something in her mind, but the page stays blank. This is one of the most common scenes in early elementary classrooms, and it is easy to misread. The blank page looks like a writing problem. It is actually a content and purpose problem.
Read the two openings against each other. The words barely changed. What changed is the order, the timing, and one shift of perspective.
The cognition version names the misread before it corrects it. "It is easy to misread" tells the reader who has spent three years explaining the blank page as a motivation problem that she isn't about to get called out. She's about to get seen. That's one of our three voices, the one who can diagnose a situation without ever diagnosing the person.
Then it shows you the wrong frame on purpose before swapping it. "The blank page looks like a writing problem" sits there for a beat before "it is actually a content and purpose problem" replaces it. The language-only version just gave you the right answer. The cognition version lets you hold the wrong one first, which is the only way a reframe connects with a reader. That's the second voice, the one who always shows you the frame already in your head before offering a better one.
And in the body, the cognition version names the thing outright, which turns a description into something you can say in a meeting. That's the third voice, the one who can't help moving from principle to example to what it means. The language-only version describes the same problem and never names it, so it stays abstract.
None of that is word choice. What's different is whether the writing acknowledges where your head is before it tries to move you. That's three people's way of thinking, braided into one.
Build the voice from the real people who make up the brand
A while later I ran the same process on myself. I fed in my own meeting transcripts and asked the same questions I'd asked about the three of them. What came back described someone who narrates into a problem instead of leading with the answer, someone who uses people's names mid-thought to think out loud. It caught the thing I do where I end a sentence on "so" and just trust you to finish it. (My husband has been pointing this out for years. He did not get a citation.) I'd never once described my own voice that way, and it was more accurate than anything I could have written about myself.
Something this good at capturing how a person thinks isn't neutral. It can build a voice that has a point of view, and it can counterfeit one just as easily. That's why it matters if you build a voice from the people whose work it is, the ones who know it's theirs. It's the whole difference between a brand that sounds like itself because it is itself and a brand wearing a borrowed suit.
For the kind of brand I work for, authenticity is why anyone believes us at all.
Generic AI content doesn't underperform for a brand like ours, it breaks our promise every time it's published. And nobody writes in to tell you. They just stop believing you.
Nobody writes in to tell you. They just stop believing you.
The work is not to make AI sound human. It's to make sure that when it sounds like you, it's because of the people who actually made the thing.