I'm Katie Parrott. I make stuff with words.

Essays, apps, and agents — because words are magic.

Writer. Builder. Chronic overthinker.

I obsess over AI and work at Every, make things like Tastemaker, and spend too much time teaching machines to sound like me. Mostly I'm trying to figure out how technology changes how work feels — by sharing how it's changing how it feels to me.

What I'm Working On

Every

Staff Writer + AI Editorial Lead

I write, test, and build at the edge of AI, then turn what I learn into agency readers can use.

Tastemaker

Creator

An AI writing tool that learns what good writing is to you, then teaches it back to you.

tastemaker.bot

The Curiosity Gap

Author

My personal Substack. Longer, weirder, more confessional. The stuff that doesn't fit anywhere else.

Read on Substack

Margot

OpenClaw Assistant

My personal AI assistant. She helped write and build this very website, and she's in charge of the changelog.

Bible Study

Side Project

A secular Bible study — reading scripture as literature, history, and weird ancient storytelling.

Current fixations

What I'm Thinking About

A running list of the questions that keep leaking out of what I'm publishing, testing, and building.

Current questions: Can I automate my working life without spending it managing the automation? If a model can reproduce my voice, did I protect it or make it easier to flatten? How do I love these tools without accepting a world that treats people as overhead?
01

Agents + overuse

Turning my working life into an agent workflow

I'm building an operating system for a writer who would absolutely let a useful tool rearrange her day, then trying to notice when help starts feeling like compulsion.

02

Writing + Tastemaker

Teaching AI my voice without sanding myself down

Tastemaker began as a way to teach AI my preferences. The live wire is whether specifying my voice protects its weirdness or gives the machine better instructions for smoothing it out.

03

Work + moral panic

Reconciling my AI enthusiasm with human dignity

I built an AI Pope to argue with an AI CEO because apparently this is how I process automation, career advice, human worth, and my own inconvenient affection for the tools.

Selected Essays

Changelog

Vibe Check: Opus 4.8—Anthropic Should’ve Rounded Up to 5

Opus 4.8 is the most complete model Every has tested yet: a jump back to the top on senior-engineering and writing benchmarks, stronger for everyday knowledge work, and good enough to make Claude tempting again—even if the app still lags the model.

Read on Every

Codex for Knowledge Work

A power-user's guide to turning OpenAI's coding agent into an operating system for knowledge work, with setup, workflows, and a seven-day starter plan.

Read the guide

The AI Pope, My Boss, and Me

I build the kind of AI Pope Leo XIV is warning about. I also work for the man making the optimistic case. So I put AI versions of all three of us in conversation, grounded in Magnifica Humanitas, After Automation, and my Working Overtime essays.

Start the dialogue

Connect your agent to Tastemaker

Tastemaker turns the passages you collect into a style guide that names your taste. Now you can connect that taste profile straight to your agent — Claude, ChatGPT, or Codex — with one-click OAuth, so it pulls your style guide and clips and writes in your voice.

Try it

How to Start a Career When AI Is Doing Your Entry-level Job

Four pieces of unsolicited advice from an AI-pilled millennial: chase meaningful problems instead of job titles, build one core craft, make portfolio work on your own, and use AI as a personal career coach.

Read on Every