Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As such, correctness depends not only on the output of individual model calls, but also on how to best adapt when incorporating new evidence or revising prior conclusions. However, existing frameworks rely on imperative control loops, ephemeral memory, and prompt-embedded logic, making agent behavior opaque, brittle, and difficult to verify. This paper introduces Credo, which represents semantic state as beliefs and regulates behavior using declarative policies defined over these beliefs. This design supports adaptive, auditable, and composable execution through a database-backed semantic control plane. We showcase these concepts in a decision-control scenario, where beliefs and policies declaratively guide critical execution choices (e.g., model selection, retrieval, corrective re-execution), enabling dynamic behavior without requiring any changes to the underlying pipeline code.

翻译：智能体AI系统在需要长期、有状态决策且条件不断演变的领域中变得日益普遍。因此，正确性不仅取决于单个模型调用的输出，还取决于在引入新证据或修正先前结论时如何最优地调整。然而，现有框架依赖于命令式控制循环、瞬时记忆和嵌入提示的逻辑，导致智能体行为不透明、脆弱且难以验证。本文提出Credo，它将语义状态表示为信念，并使用对这些信念进行声明的策略来规范行为。该设计通过基于数据库的语义控制平面支持自适应、可审计和可组合的执行。我们在一个决策控制场景中展示这些概念，其中信念和策略以声明方式指导关键执行选择（例如，模型选择、检索、纠正性重新执行），从而无需对底层管道代码进行任何更改即可实现动态行为。