Feature Store

Purpose

Manage ML features through their lifecycle: define feature definitions, compute from batch/streaming sources, serve at low latency for online inference, and generate point-in-time correct training datasets.

Agent Protocol

Trigger

Exact user phrases: "feature store", "Feast", "Tecton", "feature engineering", "feature serving", "feature registry", "point-in-time join", "online features", "offline features", "feature pipeline", "feature retrieval", "feature management", "ML feature".

Input Context

Before activating, verify:

• ML framework (PyTorch, TensorFlow, scikit-learn)
• Inference mode (batch scoring, real-time API)
• Feature sources (data warehouse, streaming, real-time APIs)
• Infrastructure (Kubernetes, cloud provider, on-prem)
• Online serving requirements (latency, throughput, freshness)
• Existing feature definitions location