Thin integration layer around a managed AI API, where most intelligence lives in an external provider and the application focuses on prompts, inputs, routing, and post-processing.

The time-series pattern focuses on modeling data that is indexed by time to capture temporal dependencies, trends, and seasonality. It uses statistical, machine learning, and increasingly foundation-model-based approaches to forecast future values, detect anomalies, and understand temporal patterns. Models typically leverage lagged values, rolling windows, temporal embeddings, and exogenous variables to learn how past and contextual signals influence future behavior. This pattern underpins operational forecasting, monitoring, and control in many data-driven systems.

Recommendation Systems (RecSys) predict what items a user is most likely to engage with, buy, or value, then rank and surface those items from a large catalog. They typically combine signals from user behavior, item attributes, and context using methods like collaborative filtering, content-based models, and deep learning–based ranking. Modern RecSys are end-to-end pipelines that ingest logs, build features and embeddings, train candidate generators and rankers, and continuously evaluate and update models in production.