Abstract: A multi-agent framework for generating synthetic data includes a human-in-the-loop agent that receives schema definitions, optional seed data, and domain-specific context, and transforms such inputs into a structured schema JSON; and an orchestrator agent that decomposes electronic data generation into subtasks and invokes autonomous agents including a topic modelling agent, an input enrichment agent, a variability injection agent, and a data generation agent. The topic modelling agent employs a large language model with an extended context window to extract hierarchical categories and salient keywords. The input enrichment agent expands categories using retrieval, keyword expansion, and iterative refinement, while the variability injection agent produces structured variation artifacts simulating real-world irregularities.

Abstract: In certain examples, a method includes obtaining an app policy comprising an application match condition and a node match condition corresponding to a node capability; assessing nodes of a clustered environment to identify a node matching the node match condition; generating, by a node manager, a node label corresponding to the node capability; associating the node label with the node identified as matching the node match condition; receiving, by an application manager, an alert that an application is to be deployed; assessing, by the application manager, the application to determine that the application matches the application match condition; updating, by the application manager, an application specification of the application to include the node label as a node selection parameter; and deploying at least a portion of the application to the node based on the node label of the node selection parameter matching the node label associated with the node.