The moat in AI writing isn't the model — it's the proprietary data you feed it
Over two years, Every writer Katie turned ChatGPT from a career coach during unemployment into a one-person content company and a compounding editor; the core discipline isn't prompting, it's using proprietary experience to close the "last mile" the model can't reach.
The video won't play here. Listen to the audio instead:
The argument · tap a timestamp to hear it
The biggest value of an AI coach wasn't saving money
After being laid off she was at a low point and couldn't afford a human career coach's hourly rate, but a $20-a-month ChatGPT subscription was manageable. She found that writing her thoughts out and letting the AI question and push back from the outside helped her externalize her thinking, counter her tendency to catastrophize, and gave her a sense of accountability. The most important legacy of that experience wasn't the money saved — it was that it convinced her AI really can drive concrete change in a life. At the time she was hesitating over whether to take Every's freelance offer, and it was ChatGPT that gave her the push to just start.
— Katie ParrottOutput capacity comes from context loaded up front, not clever prompts
She once took on a delivery load of 8 blog posts, 3 ebooks, 24 LinkedIn posts, 24 X posts and 16 Instagram posts in a week and a half. She could do it not because she knew how to write a smarter one-line prompt, but because she did a large amount of context engineering up front: feeding the model the brand messaging, product details, audience profile and differentiation all at once. And much of that demand was fundamentally content repurposing — AI is good at rewriting one long piece into versions for different platforms. The pattern she draws from it: set the scene up properly at the start, and only then can you move fast later.
— Katie ParrottGive the model a fenced playground first, then talk about tone and word choice
Before Claude Projects existed, she could only keep persistent documents in Google Docs and manually copy-paste them into context every time. This structure didn't come out of nowhere — it comes from the style guide tradition in content marketing: first define who the audience is, what the pain points are, how the product maps to them, and where the competitors and points of difference are. She says this amounts to giving the model a playground with a fence around it: make sure it won't wander off first, then talk about word choice, tone and reading level. Once Projects launched, she set up a separate project for every client and every column.
— Katie ParrottOnly a human can close the last mile in AI writing
She sees a "last mile" problem in AI writing: models have a knowledge cutoff date, and they aren't in the real physical world. So the human's job is to supply the current data and lived experience the AI can't reach. She warns that if you just toss the model a line like "write a blog post about style guides," all you get back is the generic material it already knew — commoditized information. What actually makes writing distinctive is internal company research, third-party reports, personal experience: fresh ingredients the model has never seen. The writing system is the kitchen, and the human is responsible for bringing good ingredients.
— Katie ParrottAI's value is removing friction, not producing faster
She speaks publicly about her bipolar disorder, and points out that AI's value isn't only producing content faster — it's removing friction from life. She had put off making a primary care appointment for three years, and in the end simply had Codex find a doctor who took her insurance and was accepting new patients, and book the appointment. Email is filtered by automation first, so only the messages that genuinely need a human reply reach her inbox. She says this completely resolved her email anxiety. This isn't treating AI as a production tool but as assistive technology, making the daily business of "being a person" easier to run.
— Katie ParrottLet the AI interview you repeatedly and it can set your priorities
Two years ago she was just asking ChatGPT "can you be my career coach"; today that coach lives inside a Codex project containing her role documentation, Every's brand positioning, content performance data, a folder of reader praise, and OKRs. She doesn't maintain a board herself — she uses voice conversation to have the system prioritize by highest impact, and the system maintains the Kanban for her too. The key to building this system was letting the AI question her repeatedly in the style of an interview, then settling those interviews into context. She says it feels like having a Chief of Staff rather than just a writer.
— Katie ParrottFeedback that only fixes the current draft is wasted
The core of the Compound Writing plugin is compounding thinking: every piece of feedback you give the AI should flow back into the system so the next output is automatically better. She forked Kieran Klassen's Compound Engineering plugin and rebuilt it into a writing workflow: code and writing share the same phases of brainstorming, planning, drafting and review, except writing cares more about structure, voice and evidence. Editing further splits into the substantive edit that looks at large structure and argument, the line edit that works sentence by sentence, and the final pass that checks before publication. She no longer writes in a web chat window — she pours the day's fresh material into this system instead.
— Katie ParrottVonnegut as editor gives you a perspective, not a verdict
She built Vonnegut's eight elements of story, Hitchcock's suspense principle about the bomb under the table, and the modes of expression of Sorkin and Sedaris into the plugin as editing skills. Vonnegut checks whether "the story starts as close to the end as possible" and whether "every sentence earns its place"; the Hitchcock perspective asks whether this will make the reader want to keep going. She stresses that this isn't summoning the spirit of a master to grade your draft — it's giving you a new perspective you can accept or reject. Non-professional writers may actually benefit more, because they're less inclined to pick at their own work while writing.
— Katie ParrottAI's compounding may only compound for the few who got in early
She says her core thesis about AI today is that education and access will matter more than ever. She lives in Columbus, Ohio, has never spent time in New York or San Francisco, and partly because of that she cares more about how opportunity is distributed. She admits she got where she is because she had financial slack, a time budget, and a network of excellent peers to draw on; she hopes the AI community actively creates conditions so that more places and more kinds of people can get on board. Because she sees clearly that AI has an enormous compounding effect — and the price is that the gains may compound only for the few who happened to get in early.
— Katie ParrottIn their own words · checked verbatim
Clarity, it turns out, doesn't arrive gift wrapped from a digital assistant or even a human coach. It's something I had to dig out for myself, question by question and prompt by prompt.
Natalia Quintero5:13
And our job as the humans is to close that last mile and provide the real world experiences that AI can't get because they come after the knowledge cut off and it's also out there happening somewhere in the real world and AI is not in the real world, the physical world yet.
Katie Parrott15:40
We think about AI as a productive technology, right? We value it for its ability to produce output and get things out of our, like just put stuff out. And what I found in my personal experience is that AI is just as powerful as a supportive technology.
Katie Parrott22:50
compounding is the idea that every piece of feedback that you give to AI should feed back into the system to improve the next output.
Katie Parrott32:27
My thesis on AI today is that education and access are going to matter more than they ever have before.
Katie Parrott44:49
But the risk there is that value is going to compound to the small subset of people that happen to be early. And I just think that a much more compelling vision for an AI future is one where everyone is able to come along for the ride.
Katie Parrott46:32
Figures
| Human career coach hourly rate vs. ChatGPT monthly fee | about $150/hour vs. $20/month | 3:11 |
| Time spent putting off a primary care appointment | about 3 years | 23:53 |
| Security vulnerabilities Codex found in her Tastemaker project | 5 | 43:24 |
Glossary
- context engineering
- Organizing brand, audience, product and differentiation information into fixed background material in advance, so every AI conversation runs in the right direction.
- last mile problem
- Models have a training knowledge cutoff, so humans must supply the latest data and real-world experience to keep writing out of generic boilerplate.
- compound engineering
- Settling one-off feedback given to the AI into the system, so the same good decisions take effect automatically and repeatedly in the future.
- computer errands
- Having AI agents handle the administrative chores you keep putting off — booking doctors, filing insurance, cleaning out the inbox.
How to listen
Independent writers and content entrepreneurs currently stuck on the quality of what AI writing produces, plus anyone who wants an AI agent to take over life admin and household management.
The opening minutes about being laid off and the ad break can be skipped; start at the 8:26 delivery case study for the methodology.