Ensuring AI agent reliability: ServiceNow's robust evaluation framework

SES3355

How do you know if your AI agents meet high standards for quality, safety, and reliability? Are they ready to be deployed in the real world? We believe empowering AI developers to rapidly create, test, iterate and deploy reliable and resilient agentic applications will unlock new and more valuable automation opportunities. This session explores how ServiceNow has developed its own robust framework for evaluating our OOTB AI agents, and how we are making these evaluation and testing tools available for customers and partners to evaluate their own AI agents that were built on our platform.