Prism: A Minimal Compositional Metalanguage for Specifying Agent Behavior

TL;DR

Prism is a minimal, compositional metalanguage designed for specifying agent behaviors, emphasizing simplicity, reusability, and clear separation between core logic and domain-specific extensions.

Contribution

It introduces a fixed core language with abstract combinators and a uniform approach to extending domains, enabling natural language decision rules and inspectable policies.

Findings

Demonstrated applications in thermostat, security, e-commerce, and medical domains.

Showed how Prism maps natural language rules to executable policies.

Highlighted Prism's suitability for analysis, verification, and safety constraints.

Abstract

Prism is a small, compositional metalanguage for specifying the behaviour of tool-using software agents. Rather than introducing ad hoc control constructs, Prism is built around a fixed core context, Core1, which provides a minimal background grammar of categories numbers, strings, user prompts, tools together with abstract combinators for booleans, predicates, pairs, and lists. Agent policies are written as ordinary expressions using a single abstraction operator so that conditionals appear as selections between alternatives instead of imperative if-else blocks. Domains extend the core by defining their own context-mini-grammars that introduce new categories, predicates, and external tools while reusing the same compositional machinery. We illustrate this with worked examples from thermostat control, home security, e-commerce recommendation, and medical monitoring, showing how natural language decision rules can be mapped to inspectable, executable policies. From a linguistic perspective, Prism enforces a clear separation between a reusable grammar-like core and domain specific lexicons and treats tools as bridges between internal policy representations and the external world. From an engineering perspective, it offers a compact interface language for agent control, making the space of possible actions explicit and amenable to analysis, verification, and safety constraints.