All systems operational·50+ combined years · 14 verticals · UK HQ
IoT-WorkS
home/ai telemetry
/ ai telemetry · ml platform

Models that learn from every
sensor you've ever shipped.

IoT-WorkS Telemetry AI ingests live sensor streams, learns per-asset baselines, and turns raw readings into anomalies, predicted failures and natural-language insights — explainable, auditable, hosted in the UK.

Inferences/day
1M+
Avg model accuracy
96.4%
Edge-capable
100%
model · cold-chain.compressor.lstm-v3
online
predictionpriority high
REEFER-12 compressor failure window: 7–11 days
94% confidence · σ-shift detected at 03:14
predictionpriority low
DC-1-FRIDGE-08 cycling within baseline
99% confidence · no action needed
model driftmonitoring
PSI: 0.04 · within tolerance
/ capabilities

Four layers of intelligence on every data point.

01DETECTION

Anomaly detection

Per-asset baselines learned online — isolation forest + LSTM ensemble flags drift, spikes and signature changes that fixed-threshold rules miss.

  • Streaming + batch detectors
  • Auto-baseline per asset, per shift, per season
  • False-positive feedback loop from operators
02PREDICTION

Predictive maintenance

Time-to-failure with calibrated confidence intervals. Models trained on your fleet's own history, not a generic vendor dataset.

  • Survival models (Weibull, Cox proportional hazards)
  • Confidence intervals, not just point estimates
  • Auto-creates a job in the Booking Engine when triggered
03QUERY

Natural-language queries

"Which reefers in Manchester ran above -18°C for more than 30 minutes last quarter?" — answered against a structured semantic layer, not freeform RAG over PDFs.

  • Semantic layer over MQTT + warehouse data
  • Audit trail — every answer cites the rows
  • Slack, Teams, portal, API access
04EDGE

Edge inference

Run quantised models on our gateways for sub-second latency and offline operation — sites with patchy 4G keep working, only summaries hit the cloud.

  • ONNX-Runtime + TFLite on ARMv8 gateways
  • OTA model updates with rollback
  • GDPR-friendly: raw data can stay on site
/ architecture

From the sensor to the decision — in five layers.

Built on open standards. No vendor lock-in. Edge to cloud, with the option to keep raw data on-site for GDPR-sensitive deployments.

01 · device

Sensors

LoRa, NB-IoT, Cellular, BLE — temp, humidity, vibration, current, GPS.

02 · edge

Gateways

ARMv8 + ONNX runtime. Sub-second inference, offline-first.

03 · transport

MQTT + REST

TLS, mTLS-capable. Buffered forwarding when network drops.

04 · ml core

Vize ML Engine

Online learning, drift monitoring, model registry, semantic layer.

05 · surface

Vize Portal

Dashboards, alerts, NL query, REST + webhooks for your stack.

Integrates with what you already run

connectors as of 2026.05
MQTT
OPC-UA
Modbus TCP
REST · webhooks
Azure IoT Hub
AWS IoT Core
Snowflake
PostgreSQL
Slack · Teams
Power BI
Grafana
Loxone Miniserver
/ next step

Bring your own telemetry. We'll show you what's hiding in it.

Send 30 days of historical data — we'll run our anomaly + predictive engines and walk you through what we found.