通过实时 Web 检索和可验证引用 grounding 企业 AI

By Anchal Nigam, Ashish Gite, and Kumar Kasimala.

作者：Anchal Nigam、Ashish Gite 和 Kumar Kasimala。

In our Engineering Energizers Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Anchal Nigam, a Senior Software Engineer at Salesforce, who engineers new capabilities in Prompt Builder that ground enterprise AI prompts with live external data and verifiable citations, enabling prompts to combine enterprise data with real-time external information.

在我们的 Engineering Energizers Q&A 系列中，我们突出 Salesforce 各领域推动创新的工程人才。今天，我们聚焦 Anchal Nigam，Salesforce 的一位高级软件工程师，她在 Prompt Builder 中开发新功能，这些功能使用实时外部数据和可验证引用来 grounding 企业 AI 提示，从而使提示能够将企业数据与实时外部信息结合。

Explore how the team extended Prompt Builder to ground AI prompts with external web retrieval for workflows requiring information beyond internal CRM datasets and engineered citation architecture that allows users to verify AI-generated responses against original sources to reduce hallucination risk.

探索团队如何扩展 Prompt Builder，通过外部 web 检索为需要超出内部 CRM 数据集信息的流程提供 AI 提示 grounding，并设计了引用架构，允许用户将 AI 生成的响应与原始来源验证，以降低幻觉风险。

What is your team’s mission as it relates to expanding Prompt Builder with web retrieval and citation capabilities for AI prompts?

您的团队在将 Prompt Builder 扩展为 AI 提示添加 web 检索和引用功能方面的使命是什么？

Our team makes enterprise AI systems useful and trustworthy by ensuring prompts incorporate the right data and generated responses remain verifiable. In many organizations, AI responses influence real business decisions, so the system delivers both intelligent outputs and transparency regarding information sources. We designed Prompt Builder to help prompts safely access broader sources of information while maintaining the reliability, safety, and traceability required for enterprise workloads.

我们的团队通过确保提示纳入正确的数据并使生成的响应保持可验证性，来使企业 AI 系统实用且值得信赖。在许多组织中，AI 响应会影响真实的业务决策，因此系统既提供智能输出，也提供关于信息来源的透明度。我们设计了 Prompt Builder，以帮助提示安全地访问更广泛的信息来源，同时保持企业工作负载所需的可靠性、安全性和可追溯性。

Prompt Builder enables teams to create reusable prompt templates that dynamically inco...