Abstract gradient with rounded corners, blue and purple color scheme background.

Detect drift early in complex systems

Semarx compares what a system does with what comes back. When the two stop matching, it shows where the change started, so teams can act early: service a robot, check an AI pipeline, or reroute a shipment.

One method. Many applications.

Robots and RL agents: early wear and drift, read from the robot's own signals. Proven on 2,122 recordings from a six-axis arm across 12 physical fault types, ahead of six of seven published baselines.

Supply chains: each shipment predicts its own path, and the network learns from all of them. Planners see what to watch, when to replan, and what the next shipment should expect.

AI and LLM systems: drift in LLM pipelines, caught with no model access and no retraining.

We help teams pilot, tailor and license this measure in their own systems.

Drift: What the Scores Do Not Show

Scores can look normal while a system drifts. The information monitor checks whether what the system sees, does and gets back still fit together, using only data the system already produces.

Comparison: usual monitoring checks each signal or score on its own; the information monitor checks whether what a system sees, does and gets back still fit together, using only normal operation data from the system itself, and indicates roughly where a change occurred.

Illustrative schematic: the task score stays flat while the system drifts; the information monitor departs from its healthy baseline when drift begins, well before the score drops.

Diagram: an AI agent's actions and observations. When it stops working, the information monitor helps tell whether the agent changed (actions side) or its environment changed (observations side).

ABOUT US

Measuring Drift with Information Theory

Information theory measures how much one signal reveals about another, with no model of the system needed. We use it to track how strongly inputs, actions and outcomes still inform one another, against the system’s own healthy baseline.

The Information Digital Twin (IDT)

Drift Detection for Machines, AI and Supply Chains

Information Digital Twin architecture for non-invasive AI assurance.

The IDT is our drift detector for complex systems. It runs alongside a robot, an RL agent, an LLM pipeline or a supply chain, reads only what goes in and what comes out, and computes information-theoretic metrics from that stream.

When drift appears, it gives a first indication of where, on the sensing side or the acting side, so the team knows where to look.

At its core is the information monitor, available today for robots, RL agents and LLM pipelines: no model access, no retraining.

The Human Digital Twin (HDT)

Drift Detection for Human-Machine Teams

The HDT applies the same information monitoring to the interaction between a human operator and their system, in cockpits, control rooms or clinical settings.

It reads the interaction stream: actions, observations and outcomes. When operator and system stop predicting each other, the HDT flags the drift.

Systems can then simplify the interface or alert a supervisor while the situation can still be recovered.