The instrument explained.

Each agent occupies one of four states — Susceptible, Adopter, Quiet, Detractor — and transitions probabilistically per tick. Adoption hazard combines an exogenous innovation term p with an endogenous imitation term q·φ⁺, modulated by role-based friction f and dampened by negative social pressure φ⁻.

Churn isn't a coin flip — it's gated by personal aversion and inflamed by neighbors who already defected. Detractors decay back to quiet at rate δ ≈ 0.07/tick (a half-life calibrated on firestorm literature).

Every citizen sees their in-neighbors weighted by influence. Influencers act as hubs (out-degree ×10). Department Heads form team-trees (10 strong ties ×4 weight to their reports). Cautious buyers, CFOs, and Heads require ≥2 distinct adopter contacts before social proof counts — Centola complex-contagion.

22% of the city is out-of-market: they never adopt, but they can still pile on. This is the canonical case where the dashboard shows lower numbers than the marketplace narrative.

The compliance bias of LLM personas is the #1 documented failure of synthetic research. Holon encodes resistance as a friction coefficient f ≥ 1 per role × event type. A Skeptical CFO facing a price increase has f = 4 — they need 4× the social proof of an Early Adopter to flip.

Critically: friction applies only to POSITIVE pressure. Negative signals are weighted 2.5× (negativity bias, Baumeister) and bypass the dampener. Resisting enthusiasm is human. Resisting fear is not.

The engine uses a seeded Mulberry32 PRNG. A run is a pure function of (scenario, seed) — we hash the final state to verify replay. Every shared URL is a reproducible scientific result; every backtest is a public notebook.

Date.now() and Math.random() are forbidden inside the engine. Reproducibility isn't a feature — it's how we earn the right to publish numbers.

Free runs use public industry templates (B2B SaaS seat-based, PLG self-serve, DTC). Calibrated cities (tier Scale) fit p, q, μ from your historical adoption curves (Mixpanel/Amplitude/CSV exports) and report a per-account MAPE on rétrodiction holdout.

We never claim a global accuracy figure. Accuracy is reported per account, with the holdout horizon and the seeds used. That's the only honest number.

High-stakes decisions dominated by emotion or identity (politics, sensitive products). Novel categories with no precedent. Rare-event tail risk. We log these explicitly per backtest in a dedicated section.

The model is a pre-filter, not an oracle. Use it to kill bad ideas fast and protect your research budget. Run real interviews on the survivors.