Rethink the Obvious.

We craft what holds under load and expose what was destined to fail. No theater, no high-visibility vests.

research domains

combined

53+

systems

working together

58k+

data points monitored

315

hand-coded agents

evidence-first ML world model

Areas of Magnification

Where our attention falls

How complex systems behave: how evidence becomes structure, how relationships change over time, and where one butterfly can move an entire network.

Start Here

Turning observations into intelligence

Most organizations have more data than they can interpret: systems, vendors, markets, events, dependencies, and changes arriving from different directions. We bring them into one evidence-first machine learning world model, preserve where every observation came from, and trace what changes through the relationships around it.

What gets lost

What the model preserves

Your most experienced engineer leaves. Six months later, a critical system behaves unexpectedly, and nobody knows why it was designed that way.

Institutional intelligence: operational knowledge, design decisions, dependencies and outcomes remain connected to their original context and provenance.

A supplier in Asia misses one shipment. At the same time, a port is congested and energy prices spike. Each event looks manageable on its own. Production stops three weeks later.

Cross-domain intelligence: supplier activity, logistics, infrastructure, markets and external events are connected to reveal compound risks before they reach operations.

Your board asks why a major investment was approved. The people who made the decision remember the conclusion, but not the evidence that made it compelling.

Decision intelligence: evidence, assumptions, alternatives, conditions and subsequent outcomes remain connected, making the decision reconstructable months or years later.

A storm shuts down a port on the other side of the world. You do not ship anything through it yourself. Six weeks later your own delivery times start slipping, and nobody can say why.

World intelligence: geopolitical events, trade routes, commodities, infrastructure, suppliers and business dependencies are continuously connected across the external world.

Fuel gets more expensive. Then shipping costs creep up. Then the price on your own invoice quietly rises with it, and nobody remembers when it started.

Causal intelligence: environmental, economic and operational signals are tracked through time so the model can trace how distant events propagate into business conditions.

Research Cooperation

Built alongside our coop partner

The Emergent Interaction Lab and RFI-IRFOS are independent entities with distinct research and engineering roles. Laura Serna Gaviria leads the Lab's research architecture; RFI-IRFOS develops and operates technical systems only where a specific collaboration is agreed and explicitly attributed.

Laura Serna Gaviria

Live API

Emergent Interaction Lab · Coop Partner

Research into human-AI interaction since 2023, now a working SWAT architecture: 18 hand-authored core agents lead a 292-agent pool, dispatched one at a time through a Mission Control turntable so nothing gets rushed or dropped. Every run passes a hardened review loop before anything ships, with call-laura as the final gate. Her name stays on what it produces because she built the judgment it runs on, not as a courtesy credit.

GitHub · rfi-irfos lauras-core v0.2.0 lauras-team v0.2.0 (auf Anfrage)lauras-mcp v0.2.0 lauras-api v0.2.0 OSF · HC9ZB OSF · QCVJB OSF · UXCJE

call-laura · lauras-agents · lauras-agents-public · coevolution-factory

Contact & Disclosures

Reach out

One form, even if it's just a first talk: a question, a service inquiry, research collaboration, or a security finding. Findings come to us directly, never through a third-party bug bounty platform. We would refuse to be routed through one ourselves.

Not sure what to pick on the right? General inquiries reaches a human either way - or email one of these directly.

Sending a security finding? See our full disclosure-handling policy - triage, lawful basis, and your choice of credit.

Regardless of the nature of your request, expect a reply from one of our actually human team members within 12h after it hits our inbox.