Predictive AI / Machine Learning

Real-time predictive inference

Deployed ML models score incoming data as it arrives in a workflow - per-asset, in parallel, at-scale. Every prediction is available to downstream logic nodes immediately. No batch scoring, no separate inference service, no latency between data arrival and prediction output.

Anomaly detection + automated response

Configure workflows where an anomaly detection model scores a sensor reading and a Rule Builder evaluates the score against a threshold. If the prediction indicates an anomaly, an automated action fires - maintenance alert, control command, or escalation - before a failure occurs.

Closed-loop self-optimising workflows

Chain prediction outputs with control output nodes. The model predicts an optimal state; the output node adjusts the connected system accordingly. As new data arrives, the model re-evaluates and the loop self-optimises - without human intervention at any step.

Predictive analytics dashboards

Surface model predictions, confidence intervals + historical actuals in ML Chart widgets on any dashboard. Operators see forecasted outcomes alongside live operational data in one view - giving context to current performance against predicted trajectory.

Digital twin + model testing

Test ML algorithms against isolated historical data before deployment. Run multiple models in parallel against the same dataset, compare performance metrics side by side + select the best-performing model. Deploy with confidence, not guesswork.

Continuous model retraining

Cassandra accumulates operational data continuously. Models can be retrained on an updated dataset at any time - on a schedule or on-demand. As operational patterns change, models adapt. Retraining does not require rebuilding the deployment workflow.

Predictive AI sits in the Execution Layer as the intelligence stage of every workflow - evaluating incoming data and determining what action to take based on what the model predicts.

Training data comes from the Data Layer - Cassandra time-series + Primary Table records.
Deployed models receive live data from upstream workflow nodes + Integration Layer sources.
Prediction outputs pass to logic nodes (Rule Builder, Conditional Filter) for threshold evaluation.
Control + output nodes fire the configured automated response.
The Presentation Layer surfaces predictions in ML Chart widgets on dashboards.

AI Models + Training (Data Layer) covers building, training + storing ML models on your operational data. This page covers deploying those trained models into live workflows - where predictions trigger real-time automated actions, alerts + control outputs. Training creates the model; deployment makes it act.

Classification, regression, anomaly detection, time-series forecasting, clustering + reinforcement learning. Any Python-based algorithm works - no restrictions on model type, library usage or complexity.

Yes. A prediction output feeds directly into a Rule Builder or Conditional Filter node. If the prediction meets the configured condition, the workflow fires the output action automatically - alert, control command, API call or database write. No human step required unless specifically configured.

Models score data as it arrives in the workflow - event-by-event for streaming data, or on a configured schedule for batch evaluation. For high-frequency IoT streams, per-asset iterative execution means each asset's data is scored independently and simultaneously.

Cassandra continues accumulating new operational data. Retraining the model on the updated dataset refreshes its accuracy. Automated retraining on a schedule is configurable. Model performance metrics are tracked in the platform and can be used to trigger a retraining workflow.

Yes. The ML Chart widget displays forecasts, confidence intervals + historical actuals on any dashboard. Real-time sensor data and predicted outcomes appear side by side - giving operators context for current performance against expected trajectory.

A model can be configured to run against isolated historical data in a test environment before deployment. Multiple algorithms can be tested against the same dataset simultaneously, with performance metrics compared side by side. Only the selected model is deployed to the live workflow.

Yes. Prediction outputs can pass to a GenAI / LLM connector node within the same workflow. This enables natural language explanations of what the model predicts, conversational queries about forecast trends + AI-generated recommendations based on predicted outcomes.

Yes. Prediction values can be written to a Secondary Table + exposed via an authenticated GET endpoint. They can also be pushed to external systems via Output to HTTP (webhook), Output to FTP or any output node within the same workflow chain.

The no-code model deployment interface + visual workflow builder make prediction-driven automation accessible to technically proficient users without data science backgrounds. Data scientists can access the full Python environment directly for custom algorithm development.

Partners

Sectors

Job Roles

Enterprise

Library

Our Company

Predictive AI / machine learning.

Predictions that act, not just inform.