Data Aggregator is the platform's data processing engine. One side uses cloud AI models to analyze, summarize, and extract patterns from any data you collect. The other side runs local machine learning models that classify, predict, cluster, and detect anomalies with zero per-request AI costs once trained. Both sides are fully accessible through the API, so anything you build here plugs directly into Chain Commands, chatbot responses, broadcast targeting, and every other app on the platform.

The AI analysis commands take any data you send and return structured summaries and insights. Point it at customer feedback and get the most common complaints ranked by frequency. Feed in transaction records and get spending patterns and outliers. Configure dataset summary jobs with custom AI prompts, data limits, and model selection, then run them on demand or schedule them as background jobs. Every result is stored in your account and available through the API, so you can automatically push fresh analysis into a chatbot knowledge base, drop it into broadcast messages, or pass it along in a Chain Command workflow.

Conversation consolidation compresses long conversation histories from chatbot, live operator, SMS, and email channels into compact summaries while keeping the most recent messages verbatim. When a conversation grows long, the older portion gets summarized into a narrative and merged with the recent messages so full context is preserved without the storage and processing overhead. This runs automatically with the platform's conversation management system across every channel.

Custom ML pipelines let you train and run your own machine learning models directly on the platform. Choose from 18 algorithms across four categories: classifiers that assign category labels like spam detection, sentiment analysis, and intent sorting; regressors that predict numeric values like prices, scores, and demand forecasts; clusterers that discover natural groupings in unlabeled data; and anomaly detectors that flag unusual inputs after training on clean data. Models that support incremental training can learn one example at a time through the admin panel or the API. Batch-trained models use a managed dataset file and retrain on demand. After training, all predictions run locally with no cloud AI costs.

Build pipeline sequences that chain multiple models together, where each step's output feeds directly into the next step's input. Enable live training and every model in the sequence learns from real predictions automatically. Call any function through the API - predict through a pipeline, analyze data with AI, consolidate a conversation - and wire them into Chain Commands to build full automation. Classify incoming messages with a pipeline, branch on the result, trigger different follow-up actions per category, and combine local ML predictions with AI-powered analysis in a single automated sequence.

• Send any data array to AI for analysis and get structured summaries with patterns, groupings, and outlier detection.
• Configure per-dataset summary jobs with custom prompts, data size limits, and AI model selection.
• Run summaries on demand through the API or as scheduled background jobs.
• Conversation consolidation compresses long chatbot, SMS, email, and live operator histories while keeping recent messages verbatim.
• 18 local ML model types across classifiers, regressors, clusterers, and anomaly detectors running on Rubix ML.
• Incremental training for supported models - train one row at a time without rebuilding from a full dataset.
• Batch-trained models use a managed dataset stored in S3 with retrain on demand through the admin panel.
• Pipeline sequences chain multiple models together, passing each prediction as input to the next step.
• Live training mode trains every model in the sequence automatically from real predictions.
• All functions available as API commands: predict, aggregatedata, summarizeconversation, summarizedataset, trainmodel.
• Full Chain Commands integration for building automated workflows that combine ML predictions with AI analysis and other app commands.