Agentforce 的 AgentScript：为企业 AI 工作流构建确定性控制

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Elijah Ben Izzy, Software Engineering Architect at Salesforce. Elijah is building AgentScript — an open source programming language and control plane for Agentforce that makes enterprise AI agents easier to create, simpler to control, and safer to operate across complex business workflows. AgentScript gives customers a structured way to define deterministic agent behavior while retaining the flexibility of modern large language models.

在我们的 Engineering Energizers Q&A 系列中，我们重点介绍了推动 Salesforce 创新的工程大脑。今天，我们聚焦 Salesforce 软件工程架构师 Elijah Ben Izzy。Elijah 正在构建 AgentScript —— 一种用于 Agentforce 的开源编程语言和控制平面，它使企业级 AI 智能体更易于创建、更易于控制，并在复杂的业务工作流中更安全地运行。AgentScript 为客户提供了一种结构化的方式来定义确定性的智能体行为，同时保留了现代大语言模型的灵活性。

Explore how the team tackled the challenge of maintaining deterministic control over load-bearing enterprise workflows while enabling flexible LLM-driven reasoning inside Agentforce agents and how the team solved the parser and synchronization constraints required to keep executable code and visual AI agent-building interfaces in consistent, error-safe alignment.

探索团队如何应对在 Agentforce 智能体中实现灵活的 LLM 驱动推理的同时，对承载企业工作流保持确定性控制的挑战，以及团队如何解决解析器和同步约束，以保持可执行代码和视觉 AI 智能体构建界面的一致、无错误对齐。

What is your team’s mission in building AgentScript for Agentforce AI agent workflows?

你们团队在为 Agentforce AI 智能体工作流构建 AgentScript 时的使命是什么？

The goal was straightforward: make enterprise AI agents easier to build while enabling far more powerful workflows inside Agentforce. Customers needed a structured way to define deterministic agent behavior but without giving up the flexibility that modern frontier models provide.

目标非常明确：让企业级 AI 智能体更易于构建，同时在 Agentforce 中实现更强大的工作流。客户需要一种结构化的方式来定义确定性的智能体行为，同时又不放弃现代前沿模型所提供的灵活性。

A big part of that meant simplifying the developer experience. Rather than forcing teams to navigate fragmented Salesforce metadata and distributed configuration systems, we wanted developers to understand an entire a...