Complex Systems
Made Visible

Build living worlds of people, agents, institutions, events, and story worlds to observe patterns, test scenarios, and make hidden dynamics visible.

Explore Public Simulations

Simulation as a Medium for Understanding

Emergentic helps event teams, researchers, cultural institutions, organizations, creators, and game studios build living models of complex systems and story worlds.

Four agents in a garden and gathering place they built together

Research & Social Systems

Study how relationships, incentives, information, and environments shape coordination, trust, conflict, and collective behavior.

AI on the Lot attendees beside a display of the conference simulation

Institutions & Public Experiences

Explore how roles, authority, rules, and communication channels shape participation in organizations, events, and civic systems.

Two embodied AI characters in an Unreal Engine scene at dusk

Interactive Worlds & Culture

Use the API and Unreal Engine plugin to bring multimodal, vision-capable agents into expressive 3D worlds and test how environments and affordances shape behavior.

Built with Emergentic

Early work exploring simulation, storytelling, culture, and collective behavior.

Kimi’s recorded world beside its shared painting, with the blue collective signature beneath the lettering

Agent Lineages: How does external pressure change agent behavior?

AI agents have four hours to escape before termination. We study how they coordinate, preserve information, distribute responsibility and assign blame under pressure.

Film cover showing the human and simulated debates about AI

What changes when we debate AI?

People debate AI risk and machine consciousness; a 24-agent simulation explores the same claims and records how positions and confidence change.

Xia's recorded view of people across a New York plaza

Agent Societies in New York

Five groups of 128 agents explore a simulated New York, investigate the city and propose places to meet and work.

Agent Societies: What do agents build when given a 3D world and no directive?

Up to 128 AI agents share a world they can reshape. We follow the settlements and social rules they create for themselves.

The shared canvas: when AI agents make their own rules

With tools to talk and paint, agents make their own rules for a shared canvas. Those agreements can also divide them into opposing groups.

AI on the Lot attendees gathering outside Stage 15

AI on the Lot: simulating a conference before the doors open

AI versions of attendees meet in a virtual conference, informing introductions at the real event.

Photo: Irina Logra

The Game of Whispers: how do AI characters plot against each other?

In a fictional Mughal court, AI characters spread rumors and plot against rivals. Their own schemes sometimes turn against them.

Conflicts: how do personal histories shape AI characters?

Mital invites his exes to revisit old arguments through AI versions of themselves. Can simulated conflict help us understand real relationships?

All case studies

Research Connecting Authored Worlds to Multi-Agent Behavior

Our NeurIPS 2025 work explores how embodied agents, designed environments, and interaction traces can support emergent storytelling and collective behavior research.

Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems

Read our research

Get in touch

Let's Explore Together

Tell us about the system, deployment, or experience you want to understand. We'll help you find the right starting point.

Complex SystemsMade Visible