Current State  /  Phase One  /  2026

An app where you talk, and a story talks back.

Think of the best storyteller you know. Someone who remembers every detail, adjusts on the fly, and never breaks the spell no matter what you throw at them. Storyteller is trying to be that.

Storyteller  •  Phase One Report  •  Internal

Scroll
01

Inside
The Engine

"Hesitate, and it notices. Be rude to someone in the story, and they remember."

When you start a session, a voice called the Narrator takes over. It describes the world, plays the characters, and reacts to whatever you say. Explore every corner of a room, and the descriptions get richer. The story bends around you without any special effort on your part.

The person who builds a story is called an Author. Authors use a separate set of tools — the Create Engine — to write stories, design characters, and set the rules. When they're done, everything packages into a single file called a .tome (or StoryPak).

A StoryPak runs on the Play Engine the way an app runs on a phone. Stories can't touch each other. One engine, many stories.

Voice — 01
The Narrator

Describes the world, plays every character, reacts to what you say in real time.

Interface — 02
The Guide

Sets you up before a story starts. Handles settings, onboarding, and coming back after a break.

Sound — 03
The Deejay

Manages all music and sound effects in real time — reacting to the story as it unfolds.

Memory — 04
The Chronicle

Remembers everything across every session you've ever played. Nothing is forgotten.

Core — 05
Play Engine

Runs all of them, second by second. The foundation every story is built on.

02

One Thing
Has To Be
Proven

Before any of that can exist, one thing has to be proven: that an AI can run a real game correctly, in real time.

We're using a tabletop role-playing game called Open Adventure as our test case. Think Dungeons & Dragons. It's free and open-source, so there are no licensing hurdles.

It has real rules: combat, spellcasting, character abilities, a 240-term glossary where every mechanic is named and defined. That specificity is exactly what makes it useful as a proving ground.

A tabletop RPG has clear right answers. If the AI miscalculates a combat roll, you can point to exactly where it went wrong. Clear that bar, and the engine can handle any story system we throw at it later.

The Proving Ground
240

named game mechanics in the rulebook

Open Adventure

Free and open-source. No licensing hurdles. Real rules, real right answers — the ideal test case for a real-time AI game engine.

If the AI can run this correctly, it can run anything.

03

AI Doesn't
Know When
It's Wrong

"Feed it a messy rulebook and it fills the gaps with confident-sounding guesses."

The output looks fine. The rules underneath are off. By the time you notice something strange, you're six steps from where the error started.

So before the AI ever sees the rulebook, we're cleaning it up. We converted all 16 chapters into structured files and built a machine-readable index of all 445 game terms: what each one means, and how each one connects to the others. That index is the term registry.

The registry works like a map of the entire game system. When the AI needs to resolve a rule, it walks the map — everything structured, nothing guessed.

Spellcasting Check — Dependency Chain
Spellcasting Check
Spirit Points
Action Check
Difficulty Score
Range Modifier
Reality Modifier

All pulled in one structured query. No guessing.

04

An Agent
With One Job

445 terms, all written by hand, will have errors. Relationships listed in the wrong direction. Definitions with a missing mechanic. Fields left blank when the author moved on.

We built Sherlock to find them. It's an AI agent with one job: read the rulebook, check every term against the source text, and flag anything that doesn't hold up.

A human reviewer looks at every flag before anything changes. Nothing is applied automatically.

We process terms in batches, highest-priority first. The terms that connect to the most other terms go first — because a single error there ripples into every rule interaction that touches it.

Pipeline Status
4
Batches Done
$0.13
Per Term
$60
Total run cost
for the full 445-term verification pass

Pipeline running cleanly. Passing its own quality checks. Human review required before any change is applied.

05

Clear
This Bar

Current Phase
1
Verify the foundation.
In Progress

Once the registry is verified, we hand everything to the AI agent: the rulebook plus the cleaned-up term index. The agent builds its internal understanding of the game — how the rules work, how to track state, how to run a live session.

Then we test it.

01

A small room. The AI navigates a simple scene. Descriptions land correctly. The world responds.

02

A combat. Real rules. Real rolls. Every mechanic executed correctly against the registry.

03

A puzzle. Logic and player agency. No railroading. The story bends.

04

A player who has no idea. A session that feels like someone is actually running the game for them. That's the bar.

Clear that bar, and Phase 2 begins.