Use Cases · patterns
Streaming intelligence in action
Real problems on real datasets. Each demo runs actual building blocks in your browser — raw telemetry through detection to explainable assessment.
Diagnosing WiFi AP Health
Real client telemetry from an office WiFi network. RSSI, SNR, retry, and roam signals fuse into per-AP health verdicts — no AP-side telemetry needed.
See the WiFi caseDetecting Bearing Failure
A real bearing failure from the NASA IMS dataset. Vibration statistics fuse into a health assessment that flags degradation days before breakdown.
See the bearing caseCatching Process Drift
A catalyst degrades while control loops hide it. Three detectors catch growing pressure oscillations in Tennessee Eastman Process benchmark data.
See the process caseDetecting Server Latency Degradation
Average latency looks flat for two weeks. Beneath it, tail latencies grow and the noise envelope widens. Numenta benchmark data, detected four days early.
See the server caseClassifying Driving Conditions
Real GPS data from a truck on Indian highways. Three perspectives of the speed signal fuse into a classification — Highway, City, or Jam.
See the driving caseTracking Wash Cycle Quality
Real plant-floor pressure from a 90-bar pump. Per-cycle Cpk scores each wash against spec limits while spike detection tracks sensor health.
See the wash-cycle caseThese demos run real winkComposer pipelines on real datasets — public research benchmarks and anonymised IIoT data. Parameters draw from domain knowledge and standard conventions; verdict thresholds and evidence-decay rates are tuned for narrative clarity at demo viewing speeds. As the framework matures and testing deepens, assessment behaviour and edge-case handling may be refined.