How NOBU works

Most monitoring systems wait for something to go wrong. NOBU works differently — it continuously evaluates your system from every angle, and problems surface early — often before conventional monitoring raises any flag.

NOBU vs. traditional approaches

Traditional monitoringNOBU
Warning timeAfter threshold crossedBefore readings look unusual — scales with sampling rate
SetupWeeks of baseline collectionStarts immediately, no training data required
False alarmsFrequent — static thresholds don't adaptSignificantly fewer — risk levels adapt to operating conditions
ConfidenceBinary: alarm or no alarmGraded risk levels with calibrated confidence
AdaptationManual recalibration after changesContinuously adapts to operating conditions
New failure modesCan't detect what it wasn't trained forDetects emerging problems regardless of whether they match known failure patterns

Why the difference exists

Traditional: learn what's normal

Most systems build a model of "normal" from historical data, then alarm when readings deviate. This fails on new equipment, after maintenance, or for failure modes never seen before. It also means weeks of collecting baseline data before you get any value.

NOBU: track what's uncertain

NOBU evaluates your system's condition continuously against multiple scenarios simultaneously. It doesn't need to know what "normal" looks like — it identifies emerging problems by detecting when the operating pattern starts to shift in ways that precede failures.

Warning time scales with how often you sample. At one reading per minute, NOBU typically identifies emerging problems within a handful of readings — well before threshold-based alarms would trigger. The exact lead time depends on how fast the problem develops and your sampling rate.

On confidence

When NOBU reports 85% confidence, that number reflects a rigorous assessment of your system's condition, not a black-box anomaly score. It's grounded in how consistently the sensor data matches healthy operating patterns versus developing-fault patterns.

This means the confidence level is actionable: high confidence means act now, medium means increase monitoring, low means note and move on. Over time, as NOBU sees more of your system's behavior, its estimates become more precise.

Two ways to integrate

Agent (continuous monitoring)

Install the NOBU agent on a laptop, Raspberry Pi, or industrial PC connected to your sensors. It collects data, forwards it to NOBU, and you monitor results in your dashboard. Available for Linux, Windows, and macOS.

API (on-demand inference)

For Control, API Fuzzing, and Anti-Distillation services, call the REST API directly from your application. Send sensor data, system state, or API query patterns, and get back decisions with calibrated confidence levels. Billed by compute time.

Getting started

1

Choose a service

PowerSense for power quality, Predictive Maintenance for equipment health, or API services for control, security testing, and model protection.

2

Install the agent

Download the agent for your platform, set your API key in config.yaml, and start the service. Takes about 5 minutes.

3

Open your dashboard

Watch NOBU learn your system in real time. First useful predictions typically appear within an hour of data collection.

Ready to start?

From $99/month. No contracts. Cancel anytime.

Get started →