Designing Editorial Freedom in the Age of AI

Everything began one afternoon, not with a breakthrough, but with a quiet realisation. I had just finished a collection of five books I wanted to publish — nearly two years of continuous work, revisions layered upon revisions, entire sections written and abandoned in silence. When I closed the final file, I did not feel relief. I felt a strange clarity.

The traditional path was obvious. Send the manuscripts to a publisher. Let editors reshape them, smooth the edges, adjust the structure so the books would “fit” the market. I had walked close to that road before, and I knew what it meant: architecture softened, tension reduced, voice translated into something easier to sell.

I did not want my books domesticated.

I had already published close to ten titles through Amazon KDP and IngramSpark. Those projects worked well, but always with technical intermediaries — layout experts, distribution specialists, people from Fiverr who helped solve problems I did not want to learn myself. It was efficient, but each technical layer created distance between the work and its origin.

This time I chose another path. I decided to do it myself and see how far artificial intelligence could support me — not as a substitute for authorship, but as part of a system I would design consciously.

I am speaking about three concrete models: a personalised ChatGPT instance, Claude, and Gemini. Not as abstract ideas, but as specialised language partners working inside a living editorial process.

And that distinction changed everything.

I was not trying to automate writing. I was trying to design the process.

When AI Stops Being a Tool and Becomes Architecture

At the beginning, I worked the way most people do. I asked scattered questions. I requested corrections. I allowed versions to grow organically without a clear structure. Sometimes the results were brilliant. Other times they felt strangely hollow, as if something essential had been polished away.

The problem was not technical ability. The problem was the absence of a system.

Clarity arrived when I realised that each model had a different “vocation.”

• A personalised ChatGPT functioning as a narrative interlocutor, preserving tone, continuity, and emotional coherence across long texts. • Claude, reading like an engineer with literary sensitivity, strong in structure: detecting redundancy, rhythm problems, and conceptual drift. • Gemini, acting as assembler and comparator, analysing full versions, spotting invisible changes, and maintaining large-scale organisational clarity.

They were not human writers. But they were not neutral tools either. They were language partners with different strengths.

My initial mistake was believing that any single model could perform every role. The solution appeared when I stopped asking for isolated answers and began designing a workflow where each participant had a defined function.

That was the moment editorial engineering began.

What “Personalised ChatGPT” Actually Means

Before going further, I need to clarify something important.

When I refer to ChatGPT in this article, I am not talking about the default conversational model. I am talking about a personalised instance shaped through ongoing interaction, defined protocols, and memory structures aligned with my editorial philosophy.

A personalised ChatGPT is not a different machine. It is the same underlying system operating within a specific architecture — guided by constraints, roles, and long-term context. Over time, it becomes less a general assistant and more a collaborator integrated into a workflow.

This distinction matters because the real innovation is not the model itself. It is the design surrounding it.

The moment an author defines roles, limits, and structural rules, AI stops being a random generator of language and becomes part of an intentional process.

Editorial Engineering: Designing How Writing Happens

Editorial engineering is not about writing with AI. It is about designing the ecosystem where a text evolves without losing identity.

Automation seeks speed. Engineering seeks coherence.

Each section of my books began to pass through clearly defined layers: creation, normalisation, structural verification, and final integrity control. None of these layers existed to change my voice. Their purpose was to protect it.

And here emerged one of the most decisive concepts of the entire journey: integrity control.

Integrity control is not stylistic editing. It is not about making sentences sound more elegant. It is about verifying that technical processes — formatting, restructuring, translation — do not accidentally remove living content from the author’s work.

Version comparisons, structural checks, and full-text analysis became essential. Without that vigilance, AI systems naturally simplify. With it, they become allies.

The Myth of Substitution

For a long time I believed, as many people do, that systems like these might eventually replace most intellectual labour. Practical experience forced me to rethink that assumption.

AI makes errors constantly. Not dramatic failures, but subtle deviations — a shortened paragraph, a missing nuance, a structure that looks cleaner but carries less depth.

The more complex the project became, the more obvious one truth appeared:

AI does not remove responsibility from the author. It amplifies it.

When the system grows more capable, the human designer becomes more necessary, not less.

The Author as Architect of Flow

As the process evolved, my role changed. I was no longer only the writer. I became the architect of the flow through which the text moved.

Creativity and technique stopped competing. They began to coexist within a designed structure.

Editorial independence today does not mean publishing alone. It means designing the entire process — writing, revision, structure, and distribution — so that the work can remain faithful to itself.

There were tensions. Moments when protocols threatened to overshadow the content. Too many versions. Too many checks. Too much structure. I learned quickly that the system must serve the book, not the other way around.

When the method dominates the voice, it ceases to be a tool and becomes noise.

The Boundary That Defines Collaboration

Working closely with these models revealed a clear boundary. No AI possesses bodily intuition or emotional memory. It can analyse patterns and generate coherent language, but it does not live the experience that gives birth to a text.

This limit does not diminish its value. It defines it.

The human author remains the ethical and existential axis of the project. Without that presence, the system produces language, not work.

Paradoxically, recognising that boundary brings calm. We are not facing replacements for human thought. We are working with amplifiers that require direction.

From Manuscripts to Editorial Laboratory

Gradually, my collection of five books transformed into something more than a set of texts. It became a laboratory exploring how a twenty-first-century editorial structure might function without sacrificing depth.

Not a traditional publishing house with rigid hierarchies, but a flexible system where the author directs and AI executes specialised roles.

Innovation did not lie in the models themselves. It lay in clarity of design. When roles were defined, the process advanced with surprising precision. When structure weakened, invisible errors appeared.

AI does not replace human discipline. It makes discipline unavoidable.

A Quiet Cultural Shift

Today I see something I did not understand at the beginning. Current AI systems are not substitutes for human beings. They are language partners — different voices operating inside the same process.

For them to function well, they need something larger than themselves: a living architecture capable of coordinating their strengths.

Perhaps that is the real transformation of our era. Not the automation of thought, but the emergence of the author as a designer of systems.

An author who understands processes does not lose freedom. He expands it.

Closing — When the Method Finds Its Place

When I finally stabilised the editorial flow for these books, I realised that I had not only written a collection. I had built a method capable of sustaining it.

An imperfect method. A living method. One that continues to evolve.

Editorial engineering does not promise to eliminate errors or simplify creation. It proposes something more demanding: full responsibility for the creative process in an age where language can be generated without experience.

Authorship is no longer only about producing words. It is about designing the conditions in which those words remain faithful to their origin.

Because in the end, systems do not write books. Books emerge when someone refuses to delegate their voice — and learns to design a path strong enough to carry that voice intact to the final page.

© The Times of Israel (Blogs)