REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry

TL;DR

This paper introduces REGAL, an architecture that enables deterministic grounding of agentic AI in enterprise telemetry by using a registry-driven, semantic, and version-controlled approach to improve latency, efficiency, and governance.

Contribution

REGAL presents a novel architectural pattern that treats deterministic telemetry computation as a primitive, combining semantic compression and registry-driven tools for enterprise LLM grounding.

Findings

Prototype implementation demonstrates feasibility of deterministic grounding.

Improves latency and token efficiency in enterprise AI systems.

Enhances operational governance and semantic alignment.

Abstract

Enterprise engineering organizations produce high-volume, heterogeneous telemetry from version control systems, CI/CD pipelines, issue trackers, and observability platforms. Large Language Models (LLMs) enable new forms of agentic automation, but grounding such agents on private telemetry raises three practical challenges: limited model context, locally defined semantic concepts, and evolving metric interfaces. We present REGAL, a registry-driven architecture for deterministic grounding of agentic AI systems in enterprise telemetry. REGAL adopts an explicitly architectural approach: deterministic telemetry computation is treated as a first-class primitive, and LLMs operate over a bounded, version-controlled action space rather than raw event streams. The architecture combines (1) a Medallion ELT pipeline that produces replayable, semantically compressed Gold artifacts, and (2) a registry-driven compilation layer that synthesizes Model Context Protocol (MCP) tools from declarative metric definitions. The registry functions as an "interface-as-code" layer, ensuring alignment between tool specification and execution, mitigating tool drift, and embedding governance policies directly at the semantic boundary. A prototype implementation and case study validate the feasibility of deterministic grounding and illustrate its implications for latency, token efficiency, and operational governance. This work systematizes an architectural pattern for enterprise LLM grounding; it does not propose new learning algorithms, but rather elevates deterministic computation and semantic compilation to first-class design primitives for agentic systems.