From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering
This addresses the challenge of building trustworthy agents for mission-critical applications, representing a new paradigm rather than an incremental improvement.
The paper tackles the problem of brittle and unpredictable autonomous agents in production by introducing a governance-first paradigm for principled agent engineering, embodied in the ArbiterOS architecture.
The advent of powerful Large Language Models (LLMs) has ushered in an ``Age of the Agent,'' enabling autonomous systems to tackle complex goals. However, the transition from prototype to production is hindered by a pervasive ``crisis of craft,'' resulting in agents that are brittle, unpredictable, and ultimately untrustworthy in mission-critical applications. This paper argues this crisis stems from a fundamental paradigm mismatch -- attempting to command inherently probabilistic processors with the deterministic mental models of traditional software engineering. To solve this crisis, we introduce a governance-first paradigm for principled agent engineering, embodied in a formal architecture we call ArbiterOS.