How I Used AI to Make My Writing Better

I did not use AI to write these essays for me, nor is it used directly in any aspect of the process. The writing begins and ends with me: the memory, the argument, the joke, the frustration, the pattern, the lived example, the odd little connection that made the piece worth writing in the first place.

What I built was something different: an editorial system around the writing. I used AI while building parts of the tool itself, mostly in JavaScript and Python, but the system is not a ghostwriter. When it runs, it works more like an instrument panel than a writing engine. It helps me manage the full body of work, critique individual essays, detect recurring patterns, and identify places where a draft is too flat, too repetitive, too vague, too polished, or not quite itself yet.

The system has several parts:

There is a corpus management layer that tracks the entire essay library: titles, sections, categories, tags, publication status, word counts, summaries, pull quotes, card copy, metadata, and how each piece fits into the larger collection. That helps me see whether I am overbuilding one section, neglecting another, repeating a subject too often, or circling an idea that deserves its own essay.

There is an individual essay analysis engine that critiques a draft after I have written it. It looks at structure, pacing, title strength, opening strength, conclusion strength, clarity, rhythm, specificity, and whether the piece has enough lived detail. It does not replace judgment. It gives me another angle of attack.

There is a voice and consistency engine that helps keep the work recognizably mine across a large body of writing. It looks for recurring motifs, tonal drift, favorite constructions, overused phrases, category fit, thematic overlap, and whether a piece still sounds like it belongs in the same house as the others. The goal is not to standardize everything. The goal is to preserve the voice without letting my very terrible habits and other deficiencies become ruts.

There is also a style telemetry layer that measures things most writers can feel but not always see clearly: sentence length variance, paragraph length variance, lexical diversity, repeated vocabulary, passive voice, transition density, rhetorical flatness, and places where the prose may be getting too smooth or too generic. That part is especially important to me because I am not trying to make the essays sound optimized. I am trying to keep them human.

The tool also includes pattern detectors: word clouds, phrase frequency, semantic clusters, related-essay mapping, similarity checks, topic overlap, and visual dashboards that show where ideas are gathering. Sometimes the tool tells me a draft is repeating another piece. Sometimes it shows me that a throwaway line is actually the real essay. Sometimes it points out that I keep returning to a concept without naming it directly, which usually means there is more to dig out.

There is also the Atlas Curioso, a curiosity and demand-mapping system built with AI-assisted code that ingested the full body of my work and connected it to the questions people are actually asking online. It takes search phrases, trend data, keyword fragments, and incoming site traffic, then expands them into semantic neighborhoods: related questions, emotional motives, definitions, thresholds, hidden assumptions, adjacent subjects, and gaps where honest inquiries are being answered poorly by content farms or generic AI sludge. 

The system then compares those neighborhoods against my existing essays and drafts to identify what I have already covered, what deserves a follow-up, where several smaller pieces may be gathering into a Field Note or Operating Principle, and which unanswered question might benefit from a useful human response. AI helped me build the machinery, but the Atlas does not decide what matters or manufacture the answer. It shows me where real curiosity is accumulating so I can bring judgment, experience, language, and care to the part the machines keep missing.

The editorial cockpit gives me a working view of the whole operation: what is published, what is in draft, what needs revision, what has metadata gaps, which pieces are strong, which ones need another pass, and where the library is developing its center of gravity. It turns a pile of essays into a managed body of work.

The most useful part is that the tool helps me separate writing from editing. When I write, I can follow the idea. When I revise, the system helps me ask better questions. Is this section doing work? Did I explain the point but forget to make it felt? Did I use the same move three times? Is this line actually mine, or is it just competent filler wearing a nice jacket?

AI helped ease the creation of the tool that made the writing better, but not by becoming the writer. It helped me make something that became the critic, the indexer, the pattern spotter, the dashboard, the second set of eyes, and sometimes the little warning light that says: this part is technically fine, but it needs one more human thing.

The authorship is mine but the tool helped me see the work more clearly.