在Agentforce中构建AI代理审计系统:克服数据云和Kafka集成挑战
In our “Engineering Energizers” Q&A series, we highlight the engineering minds driving innovation across Salesforce. Today, we feature Madhavi Kavathekar, a Director of Software Engineering who oversees the development of Feedback and Audit Trail, an AI auditing system within Agentforce.
在我们的“工程激励者”问答系列中,我们突出了推动Salesforce创新的工程人才。今天,我们介绍Madhavi Kavathekar,一位软件工程总监,负责开发反馈和审计跟踪,这是一个在Agentforce内的AI审计系统。
Discover how Madhavi’s team successfully integrated this system with Data Cloud, despite significant technical challenges, scaled it to manage unpredictable AI traffic using Kafka-based ingestion, and coordinated with eight to ten cross-functional teams. This solution now supports 500 enterprise customers and handles 20 million model interactions monthly, all while maintaining the highest standards of trust, security, and compliance.
了解Madhavi的团队如何成功将该系统与Data Cloud集成,尽管面临重大技术挑战,扩展到管理不可预测的AI流量,使用基于Kafka的摄取,并与八到十个跨职能团队协调。该解决方案现在支持500个企业客户,每月处理2000万次模型交互,同时保持最高的信任、安全和合规标准。
The Feedback and Audit Trail team is dedicated to designing, building, and scaling backend systems that provide transparency into AI agent behavior within Agentforce. Our goal is to create a reliable, scalable, and secure foundation for capturing and processing generative AI interaction data, enabling both internal data scientists and external customers to understand, debug, and enhance AI agent performance. The Feedback and Audit Trail feature now supports over 500 customers, making it a vital part of our AI-driven solutions.
反馈和审计跟踪团队致力于设计、构建和扩展后端系统,以提供对Agentforce内AI代理行为的透明度。我们的目标是创建一个可靠、可扩展和安全的基础,以捕获和处理生成性AI交互数据,使内部数据科学家和外部客户能够理解、调试和增强AI代理的性能。反馈和审计跟踪功能现在支持超过500个客户,使其成为我们AI驱动解决方案的重要组成部分。
Evolution of collecting generative AI feedback for deriving business impact.
收集生成AI反馈以推导业务影响的演变。
To achieve this, the team developed a robust data pipeline architecture, integrated deeply with Data Cloud, and implemented a Kafka-based ingestion model to handle unpredictable traffic patterns from global users. These efforts ensured that audit data is captured accurate...