SAP says successful AI-agent proofs of concept can falter in production
SAP executives told InfoQ that AI-agent proofs of concept may perform differently in production because enterprise data is inaccurate, business rules vary across systems, and integrations and exceptions are harder to handle. The company has released more than 300 agents and is organizing them around its existing ERP processes through Joule Work and Joule Studio, while SAP Business AI Platform provides governance and tracking.
The interview details concrete enterprise deployment challenges involving clean data, semantic consistency, permissions, testing, monitoring, versioning, and rollback, showing what SAP considers necessary beyond a successful demonstration.

“POC非常成功,领导都非常高兴,说我们就去干吧。可真正做起来,效果完全不一样,数据不准确,其他问题也都出来了。”蔡彦斌在谈及企业部署AI Agent的实际情况时直言。
企业的业务系统往往经过多年建设,数据分散在不同平台,系统之间存在复杂的依赖关系,业务规则也并不总是一致。AI Agent接入这些系统后,如何理解业务上下文、协调不同系统,以及应对生产环境中的异常情况?这些问题决定了Agent能否真正承担业务任务。
在日前落幕的SAP TechEd 2026上,AI Agent进入企业核心业务流程成为重要议题。但从技术演示到真正投入生产,仍有不少工程问题需要解决。