Over One Hundred Books in Ten Months
The Experiment
Started with mm erotica. Romantic tones, satirical edge. Pen name: Jackson Giglio. Most successful name I ever wrote under.
Then kept going. Different genres. Different styles. Testing everything.
Wanted to create my own bookstore. St. Marks Books underground energy. The Strand's massive catalog variety. Feltrinelli's intellectual range. City Lights' counterculture edge. All in one place. My catalog.
Tried everything. Erotica worked. Romance worked. Thriller worked sometimes. Noir clicked. Political satire found readers. Historical fiction. Comedy. Some books hit. Some didn't. Kept the good ones.
Script work still paid better. Script doctoring. Pitches. Been doing that almost 20 years. More profitable.
But the books kept charting on Amazon.
Over 100 books. 10 months. Real ISBNs. Actual readers. Not a typo.
The Origin: Pocket Gems
- Pre-ChatGPT. Pre-AI-hype.
Pocket Gems needed romance and erotica for mobile game launches. Post-Episode interactive fiction. Players wanted stories. Thousands of them. Fast.
My job: Write romance erotica that made players care.
The tool: Early AI language models. Primitive. Buggy. Hallucinated constantly.
The lesson: AI doesn't replace writing. AI amplifies what you already know how to do.
Early versions stumbled. Repetition. Patterns too obvious. I could see the machine thinking in circles.
Then something shifted. AI started finishing thoughts I hadn't fully formed. Anticipating moves that weren't textbook.
We were training each other. Building shared language.
Learned to prompt before "prompt engineering" was a job title. Learned character consistency. Learned pacing. Learned how to guide AI toward what the story needed without losing what made it human.
The romance erotica worked. Players engaged. Pocket Gems had great editors. Great team leaders. They taught me about tech, showed me what collaboration looked like. Inspired me to keep pushing.
Then I went rogue.
The Factory Model
Andy Warhol didn't paint every Campbell's Soup can. He built The Factory. Vision + process + assistants + repetition.
Warhol understood: Art multiplies through systems. Repetition reveals new dimensions. The machine becomes part of the vision.
Same here. Writer + AI + systematic process + genre knowledge.
Not: "AI writes books for me"
Yes: "I built a creative system where AI handles execution while I direct vision, structure, quality"
The System
Genre Research
Can't systematize what you don't understand.
Romance: meet-cute, tension, black moment, happily ever after. Tried love triangles. Love pentagrams. Love shooting stars. Structure creates freedom.
Thriller: hook, escalation, reversal. Noir pacing. Brooklyn cop investigating CEO assassination.
Erotica: tension building, consent, heat progression. Making text create physical response.
Learn the genre rules. Then build systems around them.
Character Archetypes
Genres have patterns. Build templates. Backstory. Motivation. Voice. Flaws. Arc.
AI excels at executing consistent character voice once the template is clear.
AI struggles with creating compelling characters from scratch.
Solution: You create the character. AI helps them speak consistently.
The Character Naming Problem
Over 100 books. Average 10-15 characters per book. Supporting cast. Background characters. That's thousands of names.
Can't use John, Sarah, Mike repeatedly. Readers notice.
The solution: Everyone I ever knew ended up in the books.
Friends. Bartending regulars. Comedy Cellar comics. Fashion photographers. Film crew. Pocket Gems teammates. High school. College. Family. Ex-lovers. Random encounters I remembered.
Call it an homage. Everyone I met got immortalized somewhere. Some in erotica. Some in noir. Some in satire. Some characters are composites - three people I knew merged into one fictional person.
The weird part: No one complained. Most didn't recognize themselves. Fiction transforms reality enough that names become new people.
The practical part: Authentic names feel more real than generated ones. "Xander Steele" reads like porn star. "Connor from accounts payable" reads like someone you know.
Over a thousand characters across over 100 books. That's the tribute. Your name in my books somewhere.
You're welcome.
The Collaboration
Most people either let AI write everything (garbage) or fight AI constantly (inefficient).
The actual process:
- Outline (Me) - Story structure, plot points, character arcs, themes
- Draft (Collaboration) - Feed outline + character templates, AI generates chapter, I review for consistency
- Heat Check (Me) - Does tension build right? Characters behaving true? Pacing correct?
- Polish (Me) - Remove AI tells, add human moments AI can't write, verify emotional beats land
- Publish (System) - Format, cover, upload, market, repeat
What I rewrote completely: Sex scenes. AI was technically accurate but mechanical. No humanity in the heat. Bodies moved like diagrams.
Fixed it by writing those scenes myself. Taught AI through example. Eventually it learned. Sometimes.
The split: I directed every chapter. Sometimes let AI drafts stand to see what happened. Experiment. Some sections fully me. Some collaborative. Some pure AI just to test boundaries.
Told readers this was new media exploration. Actually cared about their experience.
What Worked
Erotica ✅
Why it worked:
- Clear structure
- Character archetypes well-defined
- AI good at pacing heat progression once shown how
- Consent negotiation follows learnable patterns
Best performing: Mistress Savannah, The Boss You Need, various mm erotica under Jackson Giglio.
MISTRESS SAVANNAH
Genre: Southern Gothic
Southern belle Dom in Paris. Carnevale meets BDSM.
THE BOSS YOU NEED
Genre: Business Fiction
Corporate power dynamics. C-suite dom/sub exploration.
AI writes decent erotica once you teach it consent, pacing, and emotional beats. Then you polish the humanity back in.
Romance ✅
Why it worked:
- Genre conventions extremely structured
- Readers know what they want
- AI handles meet-cute and banter well
- Human polishes emotional vulnerability
Nothing beats love triangle. Except love pentagram. Or love shooting star.
Thriller ⚠️
Mixed results.
What worked: High-concept hooks, pacing, action sequences
What didn't: Complex plotting with multiple threads, red herrings that actually work, subtle clues paying off later
Best example: CEO assassination noir. Retired Black cop from Brooklyn investigating. Chester Himes meets James Ellroy energy. Based on real headlines.
Context: Know CEOs. Like some a lot. Understand why they're targeted. Don't label people. Try to accept everyone individually.
Thought of it as exploring power dynamics. Machiavellian games. Questions worth asking even if I don't have answers.
Worked because: Real tension. Complex feelings. Familiar territory. AI handled pacing. I handled moral ambiguity.
Literary Fiction ❌
Complete failure.
Why: Requires subtle character development AI can't handle. Voice needs distinctiveness, not generic execution. Themes emerge naturally, not stated. AI defaults to explaining instead of showing.
Some creative work resists systematization. That's fine. Not everything should scale.
