# The Grammar of Simulation

> Source: <https://simgrammar.com/>
> Published: 2026-11-22 12:37:40+00:00

**Recommendation:** When adding AI techniques that run during play to a lockstep multiplayer game, plan for one machine to stream their outputs, since 23 of 35 such techniques cannot run deterministically in lockstep.
More in the playbook "Designing agent systems": <https://wpnews.pro/playbooks/agent-architecture>

atlas simulation games, part by part

# The Grammar of Simulation

Every simulation game is assembled from a shared set of parts: production chains, needs, markets, weather, raids. Naming the parts shows why games feel alike, which combinations the catalog has not seen yet, and where AI can change how a game plays.

Here a simulation game is one whose core loop is driven by a model of some system, such as an economy, an ecology, a body, or a machine, whose state changes without the player scripting each change.

**-0.42** mechanics that generate more unscripted variety are rated harder to read (ρ across the rubric scores)

[§5.6](paper/#5-6-the-legibility-frontier)

**23 of 35** AI techniques that run during play cannot run in lockstep multiplayer unless one machine streams their outputs

[§6.4](paper/#6-4-determinism)

four findings from the paper; each links to the section that makes the case

## start with a game you know

[all 179 games](game/)

Each game drawn as the parts it is built from, core parts first. Open one to see how it does each part, and which other games share them.

episode 1 5:27

### [Every simulation game is made of the same parts](watch/episode-01/)

RimWorld taken apart into its mechanics, then every game in the catalog the same way. Most of the commonest parts simulate nothing, the parts a game can't do without are much rarer, and each genre spends its parts differently.

episode 2 7:47

### [Where the parts came from](watch/episode-02/)

Hamurabi, from 1968, already used parts that games still use. Most of the vocabulary was in a catalog game by 2000, a test against chance shows how much of that comes from parts being widely shared, and recent games are built mostly from old parts.

short 1 0:43 from [chapter 1](book/01-same-parts/) · [episode 1](watch/episode-01/)

### [The five most common parts](watch/#short-01)

Most of the parts that turn up most often in simulation games don't simulate anything.

short 2 0:41 from [chapter 3](book/03-old-parts/) · [episode 2](watch/episode-02/)

### [Every part of Stardew Valley is older than it](watch/#short-02)

Every part of Stardew Valley appears in an earlier game in our catalog.

short 3 0:36 from [chapter 4](book/04-families/) · [episode 3](watch/episode-03/)

### [A border post and a daughter](watch/#short-03)

A border-checkpoint game from 2013 and a daughter-raising game from 1993 belong to the same family.

short 4 0:36 from [chapter 5](book/05-depth-costs-legibility/) · [episode 4](watch/episode-04/)

### [Decorating makes the raids bigger](watch/#short-04)

In RimWorld, decorating your colony makes the raids bigger.

## ai that already reaches games

[all 46 techniques](technique/)

The techniques furthest along in shipped games, and the mechanics each one changes.

### [Neural rendering in the graphics pipeline](technique/neural-rendering-shaders/)

Small neural networks inside the renderer upscale frames, generate extra frames, denoise ray tracing, decode compressed textures and layered materials, and since DLSS 5 re-light the final frame, all without touching simulation state.

### [Generative agents (memory stream, reflection, planning)](technique/generative-agents/)

LLM-driven characters that store observations in a natural-language memory stream, retrieve them by recency, importance, and relevance, synthesize reflections, and plan their day top-down.

### [Agent-based automated playtesting and balancing](technique/automated-playtesting/)

Studios train imitation, reinforcement learning, and search agents to play builds, estimating level difficulty, pass and churn rates, progression pacing, map coverage, and exploits before players reach them.

### [LLM game master and narrative director](technique/llm-game-master/)

A language model that adjudicates player and NPC intentions, decides outcomes, generates events and quests, and narrates them, either free-form or checked against a typed world state and canon.

### [LLM-adjudicated state transitions (LLM as game mechanic)](technique/llm-rule-adjudication/)

A language model computes the outcome of an interaction (two elements combined, an action on an object) from a text description of the inputs, with results cached so every player sees the same rule.

### [Monte Carlo tree search for game AI](technique/monte-carlo-tree-search/)

A best-first search that grows a game tree from repeated simulated playouts and picks branches with a bandit rule such as UCT, letting AI players plan from a forward model without a hand-tuned evaluation function.

## what could be built next

[all 42 bets](opportunity/)

Design bets ranked by impact, feasibility, and novelty. Each one names a test a small team could run and a dated prediction anyone can check.

### [Why-query over the simulation log](opportunity/causal-why-query/)

Let players ask why something happened and answer from the simulation's own event log, making deep systemic games legible without simplifying them.

### [Branch preview of policy futures](opportunity/branch-preview-forecasts/)

Fork the simulation in the background and show the player likely futures of a decision before committing, using parallel or surrogate simulation.

### [Event-sourced simulation runtime](opportunity/event-sourced-sim-runtime/)

An engine layer that records simulation and model calls as an append-only event log, giving replay, forking, explanation, and determinism for games with AI components.

### [Mechanic modding by description](opportunity/language-modding/)

Players describe a rule change in plain language; a model writes the mod against the modding API and automated agents test it before it is shared.

## the book

[contents](book/)

The findings at book length, for reading straight through: what the parts are, how they trade off, where AI lands, and what to build.

### The grammar

[1. Same parts](book/01-same-parts/) · [2. Six layers](book/02-six-layers/) · [3. Old parts](book/03-old-parts/) · [4. Families](book/04-families/) · [5. Rated deep, rated hard to read](book/05-depth-costs-legibility/) · [6. Five ceilings](book/06-five-ceilings/)

### The machines arrive

### Bets and checks

### How the book is made

## the paper and the data

### [The Grammar of Simulation](paper/)

Every finding with its method and statistics, figures you can explore, and the full catalog of games and techniques. The place to check a claim.

### [How the atlas is made](about/)

Every game, mechanic, and technique is an open record with its sources, so any number here can be traced to where it came from, checked, and corrected by anyone.
