内容来源：https://www.technologyreview.com/2025/09/16/1123592/de-risking-investment-in-ai-agents/

内容总结：

【合作推广】NICE公司产品管理副总裁Neeraj Verma近日指出，人工智能代理（AI agents）的成功关键在于从设计之初就嵌入信任机制。随着自动化技术日益成为客户体验的核心驱动力，新一代“代理型AI”正推动行业向更高水平发展。这类系统能够自主规划、行动并适应动态目标，彻底改变了传统预设流程的交互模式。

Verma表示，当前用户已普遍接触过生成式AI聊天机器人，他们对客户体验的期待早已超越标准化脚本服务。对企业而言，代理型AI不仅能处理复杂服务交互、实时支持员工，还可随需求变化灵活扩展。但由此带来的非确定性系统也带来新挑战：如何测试动态响应系统？如何在安全性与灵活性间取得平衡？如何管控成本、透明度与伦理风险？

专家认为，未来客户体验技术的普及速度将取决于这些问题的解决方案。Verma强调，过去十年间行业经历了从刚性流程到生成式系统的范式转变，成功企业将聚焦结果导向设计，构建透明、安全且可规模化的工具。他预测：“真正的赢家将是那些专注应用场景的AI公司。”

（本文由MIT Technology Review定制内容团队独立制作，人工智能工具仅辅助次要生产环节并经人工审核。）

中文翻译：

赞助内容
降低AI智能体投资风险
NICE产品管理副总裁尼拉吉·维尔马指出：只有当信任从设计之初就融入系统，AI智能体才能真正蓬勃发展。

本文与NICE联合呈现
自动化已成为客户体验领域的决定性力量。从解答疑问的聊天机器人到影响选择的推荐系统，由AI驱动的工具已渗透至几乎每次交互中。但最新涌现的"智能体AI"——能够规划、行动并自适应调整以实现既定目标的系统——正将自动化推向更深的层次。

NICE产品管理副总裁尼拉吉·维尔马表示："我交谈过的每个人都至少通过手机与某种生成式AI机器人对话过。他们期待体验是非预设的。我们不仅是在提升客户体验，更是在实现客户对体验的终极期望。"

对企业而言，这种潜力具有变革性：AI智能体既能处理复杂服务交互，实时支持员工，又能随客户需求变化无缝扩展。但从预设的确定性流程转向非确定性的生成式系统，也带来了新挑战：如何测试两次响应可能不同的系统？在赋予AI系统核心基础设施访问权时，如何平衡安全性与灵活性？在追求实质回报的同时，又如何管控成本、透明度与道德风险？

这些解决方案将决定企业以何种方式、多快速度迎接客户体验技术的下一个时代。

维尔马认为，过去十年的客户体验自动化本质是期望值的演变——从僵化的确定性流程转向灵活的生成式系统。企业必须重新思考如何规避风险、设置防护措施及评估成效。维尔马指出，未来属于那些聚焦结果导向设计的组织：即构建透明、安全且可规模化工具的企业。

"我相信最终赢家将是专注场景应用的公司，即那些深耕应用型AI的企业。"维尔马如是说。

本内容由《麻省理工科技评论》定制内容部门Insights制作，并非由编辑部撰写。内容由人类作者、编辑、分析师和插画师经研究、设计与撰写完成，若使用AI工具仅限经过严格人工审核的辅助生产流程。

深度解析
人工智能
谷歌首次披露单次AI查询能耗数据
这是大型AI企业迄今最透明的评估，为研究人员提供了期待已久的内幕视角。

塑造OpenAI研究未来的两位关键人物
独家对话研究双主管马克·陈与雅各布·帕乔茨基，探讨增强推理模型与超级对齐的发展路径。

心理咨询师秘密使用ChatGPT引发客户信任危机
部分治疗师在诊疗过程中使用AI，此举正危及客户信任与隐私安全。

GPT-5正式亮相：未来何去何从？
这次备受瞩目的升级为ChatGPT用户体验带来多项优化，但距通用人工智能仍道阻且长。

保持联系
获取《麻省理工科技评论》最新动态
发现特别优惠、热门话题、即将举办的活动及更多精彩内容。

英文来源：

Sponsored
De-risking investment in AI agents
AI agents thrive when trust is designed in from the start, says vice president of product management at NICE, Neeraj Verma.
In partnership withNiCE
Automation has become a defining force in the customer experience. Between the chatbots that answer our questions and the recommendation systems that shape our choices, AI-driven tools are now embedded in nearly every interaction. But the latest wave of so-called “agentic AI”—systems that can plan, act, and adapt toward a defined goal—promises to push automation even further.
"Every single person that I've spoken to has at least spoken to some sort of GenAI bot on their phones. They expect experiences to be not scripted. It's almost like we're not improving customer experience, we're getting to the point of what customers expect customer experience to be," says vice president of product management at NICE, Neeraj Verma.
For businesses, the potential is transformative: AI agents that can handle complex service interactions, support employees in real time, and scale seamlessly as customer demands shift. But the move from scripted, deterministic flows to non-deterministic, generative systems brings new challenges. How can you test something that doesn’t always respond the same way twice? How can you balance safety and flexibility when giving an AI system access to core infrastructure? And how can you manage cost, transparency, and ethical risk while still pursuing meaningful returns?
These solutions will determine how, and how quickly, companies embrace the next era of customer experience technology.
Verma argues that the story of customer experience automation over the past decade has been one of shifting expectations—from rigid, deterministic flows to flexible, generative systems. Along the way, businesses have had to rethink how they mitigate risk, implement guardrails, and measure success. The future, Verma suggests, belongs to organizations that focus on outcome-oriented design: tools that work transparently, safely, and at scale.
“I believe that the big winners are going to be the use case companies, the applied AI companies,” says Verma.
This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review’s editorial staff. It was researched, designed, and written by human writers, editors, analysts, and illustrators. AI tools that may have been used were limited to secondary production processes that passed thorough human review.
Deep Dive
Artificial intelligence
In a first, Google has released data on how much energy an AI prompt uses
It’s the most transparent estimate yet from one of the big AI companies, and a long-awaited peek behind the curtain for researchers.
The two people shaping the future of OpenAI’s research
An exclusive conversation with Mark Chen and Jakub Pachocki, OpenAI’s twin heads of research, about the path toward more capable reasoning models—and superalignment.
Therapists are secretly using ChatGPT. Clients are triggered.
Some therapists are using AI during therapy sessions. They’re risking their clients’ trust and privacy in the process.
GPT-5 is here. Now what?
The much-hyped release makes several enhancements to the ChatGPT user experience. But it’s still far short of AGI.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.