I Started Talking to My Computer Instead of Typing. It Changed How I Think.

Was this newsletter forwarded to you? Sign up to get it in your inbox.

I didn’t notice how much typing slowed my thoughts down until I realized I’d stopped.

It hit me on a Saturday afternoon. I was minding my own business when an idea popped into my head that I knew I wanted to capture. I ran to my computer; but instead of my fingers flying to the keyboard, I started talking—and my AI assistant wrote it down.

It happens by muscle memory, as tends to happen when you do something enough times. At this point, I’ve drafted seven full articles this way. “It takes 21 days to form a habit” might be a myth, but in my case, it took around that long for the whole “talking to my computer” thing to take hold.

On the surface, nothing about typing feels laborious—I’ve been doing it since I was a fifth-grade Mavis Beacon all-star. I average 120 words per minute talking; I can hit that while typing if I focus really hard on my fingers. There are tiny frictions that slow me down, micro-decisions about phrasing and punctuation and rhythm that pull focus from where I want my thoughts to be: on the ideas.

These days, I bypass the speed bumps with a setup that’s become like an extension of my brain. First, there’s my Working Overtime workspace, a ChatGPT project I have set up to help me brainstorm ideas, do research, and flesh out drafts for my column. Then there’s Monologue, the AI-powered transcription app that Naveen Naidu Mummana, entrepreneur in residence at Every, is building (it’s currently in public beta). I just press a key to talk; Monologue relays the message; the alien superintelligence inside my project tells me what it “thinks.”

ChatGPT has its own built-in voice-to-text mode, and there are other popular voice dictation tools on the market, like Whispr Flow. But I found frustrations with each: The dictation lags, or the output is unclear, or opening the app slows down my computer to the point where I can’t use it. Using Monologue paired with ChatGPT was the first time that talking to my computer felt like the evangelists promised it would: easy.

Once I stopped treating the keyboard as my only entry point, the whole shape of my work changed: Ideas flow faster, structure emerges in conversation, and clarity comes from rounds and rounds of “How’s this?” and “What about that?” If you haven’t tried talking to your computer yet, I highly recommend it. Let me tell you why.

Building agents is no longer just for engineers

Instead of relying on ChatGPT, your team can build secure agents that fit their workflows and tools. With Vellum, AI becomes part of how your org ships faster.

1. Build agents that adapt to your workflows
2. Share and maintain composable workflows across the org
3. Turn AI into a team skill, not a silo
4. Build, evaluate, and monitor agents in one platform

Book a demo call today. Start with Vellum.

Want to sponsor Every? Click here.

Talking as a mode of work

Here’s how it looks in practice. I open a fresh chat inside my project and say, “I have an idea for a Working Overtime essay about talking to my computer instead of typing and how it’s changed the ergonomics of my work.” The first few times I did this, my dog perked her ears up from her chair in the corner, thinking I was talking to her. Now, she keeps on snoozing.

Monologue catches my words and transcribes them into ChatGPT (cleaned up for stammers and false starts, which is nice). I hit enter, my project thinks for a second, and returns a potential outline and two follow-up questions. I say, “This is close—keep the idea of ergonomics.” It generates a new response based on that nudge. Five rounds of back-and-forth later, I have an outline and an opening paragraph. This piece started that way. So did another draft I began the same day after a morning walk.

I feel like Don Draper on Mad Men, leaning back and rattling off notes for Joan to type up. Dictation used to be a form of executive privilege. Instead of a beleaguered secretary, though, I have an always-online co-worker—several, in fact. In addition to my Working Overtime project, I have another one for Source Code, the Every column where our engineers share what they’re learning through building. Then there’s the Every AI editor that’s set up in Claude, plus my AI career coach and the AI Bible study buddy I have set up in ChatGPT. All of these projects have documents uploaded to their project files that provide context for how I use that specific system, as well as custom instructions that instruct the project on how it should behave. The Working Overtime project “talks” back like an editorial assistant. The Every editor pushes back on weak stakes and lack of payoff. My career coach provides feedback when my impostor syndrome gets out of control. I keep talking because they keep returning things that get me thinking. The exchange works like an engine carrying ideas forward.

The upside is immediate: Monologue keeps the words flowing while my hands stay off the keys. The Working Overtime project carries my house style and common stumbling blocks, so it gets me to a finished draft faster than a blank document ever has. Our Every editor in Claude pressure-tests the idea against the publication’s standards. The trio makes the work feel conversational and iterative. I say, “That’s not quite what I’m thinking.” The AI pivots. Each small correction pulls the work toward the shape I meant but hadn’t yet articulated.

What makes this mode so different is the way it loosens the grip of the keyboard on the thought process. When I type, I’m always self-editing—backspacing, rephrasing, or policing awkward syntax. When I talk, the ideas tumble out in real time. It’s less linear, but that turns out to be great for brainstorming. I find myself digging into the nuances and complexities of ideas more than I did when a chunk of my mental bandwidth was eaten up by cranking out the draft.

Keeping time with machines

The collaboration comes with a trade-off, though. The same setup that makes work feel effortless also tempts me into letting it spill further into my weekends. Here I am on a Saturday speaking this essay into existence with an AI thought partner that’s ready to pick up the thread of work at any hour I feel like talking.

As a staff writer and AI editorial lead at Every, my role sits squarely in the “individual contributor” category. But sitting in my office, saying things out loud while systems around me scurry to make those things happen, I feel more like a CEO, and research shows that people higher up the ladder log longer weeks. One large study of CEOs found they worked about 62.5 hours a week, with nearly three-quarters of that time spent in conversation—meetings, calls, face-to-face talks. Maybe that’s why I feel busier the less I type.

Of course, it’s not only executives who get pulled into longer hours. Researchers call it an “entrainment cycle”—the process by which professionals become emotionally and physically synchronized with their organization's tempo. A recent study of law and accounting firms found that employees didn't just work long hours because they had to; they craved the adrenaline. When they tried to disconnect, during holidays or quiet weeks, they experienced anxiety, boredom, and even physical withdrawal symptoms.

My AI dictation setup creates this pattern. But instead of synchronizing with organizational rhythm, I'm synchronizing with algorithmic responsiveness. The machine is always ready to turn my scattered thoughts into something coherent.

Productivity looks different when you never touch the keyboard

The lesson isn’t to clamp down on myself and keep weekends sacred. Rather, it’s to recognize that this new way of working requires a renegotiation of my boundaries. Talking to machines makes work feel playful again, in a way it hasn’t since I worked in a physical office where I could peek my head over my monitor and go back and forth with a co-worker about a project we were both working on.

I think about this new mental ergonomics the way I’d think about a comfortable desk chair: It should make the hours I spend at work more comfortable, and free mental space and energy for creativity. Ease is not the enemy, but the burden is on me to keep the lack of friction from leading to fixation. I have a tendency to overwork when I feel like I'm "on to something," and this setup creates exactly the kind of rapid feedback loop that feels like hitting the dopamine jackpot.

I used to measure my productivity in hard numbers: drafts delivered, words written, and hours at the keyboard. I still track those metrics, but they tend to fade into the background in favor of more qualitative criteria: Did I articulate this argument right? Does this introduction do the work I want it to? Am I excited to pursue this idea, or work on this project? I spend my time thinking about aspects of the work that are higher up on the hierarchy of needs: structure, specificity, complexity, and nuance. I cared about these things before, but deadlines are deadlines, and there are compromises I would make for expediency’s sake that I’m less likely to make now.

Of course, there’s value in slowing down and thinking things through word by word. Clear writing is clear thinking, as many a round of revisions has taught me. I still do that thinking, but the timing of when I do it has shifted from before the words exist to after I’ve blurted them out.

It still amazes me that what began as a stray Saturday thought could snowball into this essay as quickly as it did. Who knows if it even would have made it to the page if I’d waited for the perfect turn of phrase to commit to the screen. Talking instead of typing has given me a detour around my own internal critic. Sometimes the best way of working through a problem really is to talk it out.

Monologue will come out of public beta later this month. Become an Every subscriber today to be one of the first to know when it’s live.

Katie Parrott is a staff writer and AI editorial lead at Every. You can read more of her work in her newsletter.

To read more essays like this, subscribe to Every, and follow us on X at @every and on LinkedIn.

We build AI tools for readers like you. Write brilliantly with Spiral. Organize files automatically with Sparkle. Deliver yourself from email with Cora.

We also do AI training, adoption, and innovation for companies. Work with us to bring AI into your organization.

Get paid for sharing Every with your friends. Join our referral program.