Strabo: Declarative Specification and Implementation of Agentic Interaction Protocols
2026-06-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors present Strabo, which shows how new methods for creating software agents that follow clear, rule-based interaction protocols can help real-world projects like Google's Universal Commerce Protocol (UCP). They first model part of UCP related to checkouts using a declarative language called Langshaw and build agents with Peach, a programming framework for Langshaw. Then, they demonstrate that their Peach agents can work together smoothly with Google's UCP agents, proving their approach is accurate and compatible. This work suggests that these formal techniques can gradually be adopted in existing systems without needing to replace everything at once.
multiagent systemsdeclarative protocolsAgentic AIUniversal Commerce ProtocolLangshawPeach programming modele-commerce interactionsformal specificationsagent interoperabilityEMAS (Emergent Multi-Agent Systems)
Authors
Samuel H. Christie, Amit K. Chopra, Munindar P. Singh
Abstract
The last few years have witnessed major advances in the modeling and implementation of multiagent systems based on declarative interaction protocols. Our contribution, Strabo, establishes the relevance of these advances to ongoing industry efforts in Agentic AI. Specifically, we consider UCP, the Universal Commerce Protocol, a recent Google-led effort to standardize e-commerce interactions for AI agents. Our exercise is in two parts. One, we model the part of UCP dealing with checkouts as a declarative Langshaw protocol and implement agents using Peach, a programming model for Langshaw. This part of the exercise brings out the advantages of formal, declarative specifications. Two, we show that Peach agents can interoperate with UCP agents implemented by Google, thereby establishing the fidelity of our approach with respect to UCP. Such interoperation enables the incremental introduction of declarative protocols and agents into a conventional setting, indicating a pathway by which EMAS ideas could influence practice without demanding a wholesale update.