Scientific AI workflows

Patterns combining scientific computation, experiments, and AI-assisted analysis. Each workflow below has its own page with a DAG, inputs, outputs, provenance, and execution considerations.

Workflow	Purpose
Scientific pipeline with AI interpretation	Keep deterministic science and AI-assisted interpretation independently reproducible.
Surrogate model construction	Approximate an expensive simulator using a traceable design of experiments.
Model-guided experiment cycle	Use observations to propose a constrained next experiment batch while preserving each iteration.