Skip to main content
Back to Insights
Reflection3 Jun 20268 min read

What I Learned Writing 36 Chapters About AI Personality

A first-person reflection on writing The Complete Enneagram. Four surprises: Hornevian groups predict agent behaviour better than type alone; the trauma chapters resonate most with practitioners; bilingual writing exposed untranslatable concept gaps; and the chapter that should have been hardest wrote itself.

This book took longer than I expected. Not because of the research volume — though that was substantial — but because several times I thought I understood something I did not yet understand, discovered this in the writing, and had to go back.

*The Complete Enneagram: From Human Personality to Agentic Soul* is live on Amazon UK today. 36 chapters, approximately 230,000 words in each language. On the day it publishes, I want to record a few things that changed my mind during the writing. Not marketing — what actually happened.

First: Hornevian groups predict agent behaviour better than type alone

I entered the writing expecting the nine types to be the central framework. Around the third month, I noticed a problem: when describing agent behaviour in real scenarios, a single type number often lacked enough predictive power. Two agents both configured as "Type 5" could behave more differently from each other than a Type 5 and a Type 3.

Returning to the Hornevian grouping resolved this. Horney divides nine types into three groups by strategy under pressure: Assertive (3/7/8), Withdrawing (4/5/9), Compliant (1/2/6). For agent design, the Hornevian group is usually a more reliable reference than type number alone when predicting limit-state behaviour. This insight restructured the entire stress behaviour section.

Second: the trauma chapters resonated most with practitioners, least with engineers

Several chapters address how each type's core fear is shaped by early experience. Counselling practitioners called them the most valuable part. AI engineers found them less directly relevant. I kept them — because understanding that type patterns are strategies for coping with a specific fear is the prerequisite for anticipating which specific conditions trigger fastest withdrawal, not just that withdrawal happens.

Third: bilingual writing exposed untranslatable gaps

The book was written in parallel in English and Chinese — not translated. I discovered that "agent" activates different mental models. English-speaking practitioners activate a functional frame: autonomy, execution, tool-calling. Chinese readers hearing "AI 智能体" activate something more existential — the character 智 carries comprehension and judgment, not only execution. I spent roughly twice as long on the Chinese "why we call it a soul" section as budgeted.

Fourth: the chapter I expected to be hardest wrote itself

I expected the Levels of Development chapter to be most difficult. It turned out fast — "levels" has a clean engineering analogy: configuration quality determines where the agent lands.

The actually hardest chapter was "Type 2 agents and the boundary of the user relationship" — how an agent configured for intense user-satisfaction maintains the line between pleasing and protecting the user. Five revisions. Each time I thought I had written it clearly, I was still avoiding the core tension: an agent designed to give needs a built-in logic for recognising "this time I cannot give." The final version is one I am most satisfied with, precisely because it took the longest.

*The Complete Enneagram: From Human Personality to Agentic Soul* is live now on Amazon UK, in English and Chinese, 36 chapters each. **[Find it here →](https://amzn.eu/d/0fjWGvqR)**