One Agent Workflow Ran Three Different Ways

The reported platform emerged from Amazon’s Rufus assistant, where real-time serving, background tasks and high-volume evaluation normally require different runtimes. Developers define one typed dataflow graph, which is then bound to in-process streaming, durable AWS SWF orchestration or distributed Apache Flink processing. Language-model calls become suspendable nodes whose delivery, retry and batching semantics follow the selected substrate. Dozens of production configurations across five orchestration patterns showed no detectable output-quality difference across bindings, while batch execution reduced inference cost in line with published batch pricing. The evidence is an engineering report from one production ecosystem rather than a cross-platform standard.