Production ML architecture: training-serving skew
The model is the small part. Training-serving skew, feature freshness, shadow deploys, drift detection, and monitoring that catches decay.
Tag
Every article tagged Architecture. For a structured path, browse Learn.
The model is the small part. Training-serving skew, feature freshness, shadow deploys, drift detection, and monitoring that catches decay.
An agent is a loop with tools and a stopping condition. Context growth, error handling, termination — and when to write a chain instead.
Tool calling fails at the interface, not the model. Schema design, descriptions, error contracts, and what MCP actually standardises.