AI News

ANASSA is an architecture for agentic AI systems that operate on geospatial data, where autonomous reasoning and tool use must be combined with explicit orchestration, spatial validation, governance, provenance, failure handling, and human decision authority. An earlier ANASSA framework defined high-level components and responsibility boundaries but did not explain how those responsibilities should be decomposed for implementation. This paper applies Design Science Research to derive a low-level architecture while preserving the boundaries of the original framework. The resulting design specifies 47 logical roles, versioned task graphs, capability-based agent selection, typed contracts, explicit runtime states, spatial validation mechanisms, governance controls, failure and recovery paths, and provenance records. The authors demonstrate the design with an end-to-end execution trace and evaluate it analytically for requirements traceability, internal consistency, preservation of responsibilities, and technology independence. The paper presents the result as an implementation-facing bridge to future system development. It is designed to make governed spatial agentic workflows inspectable, reconstructable, and testable without tying them to a particular AI model, geospatial platform, communication protocol, or deployment environment.