We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
I
Irina Gutman
L
Lauren Wood
Irina Gutman: 我建议企业从最简单、可重复的AI代理开始，而不是一开始就追求最复杂、最先进的代理。这有助于企业逐步适应AI技术，降低风险。
设计AI代理与人类之间的交互体验是一项新兴技能，需要持续监控和更新AI代理。
Salesforce AI 产品的创新团队能够将AI能力转化为提升客户体验的解决方案，这并非科幻小说。
生成式AI利用大型语言模型(LLM)从多个来源提取信息，而预测性AI则局限于预定义的范围内。
Waymo无人驾驶汽车是代理式AI的一个例子，它能够根据规则和数据做出决策。
代理式AI能够进行自我思考，并具有机遇和挑战。
代理式AI具有推理引擎和记忆功能，能够利用之前的学习经验进行决策。
解释了聊天机器人和AI代理之间的区别，AI代理能够理解自然语言并根据上下文做出决策，而聊天机器人则遵循预设流程。
解释了从“人工在环”到“人工+AI”的转变，强调人类仍然拥有决策权，但AI可以作为辅助工具增强人类的能力。
解释了AI代理的五个组成部分：角色、行动、护栏、数据和渠道。
建议企业从简单、可重复的任务开始实施AI代理，逐步扩展到更复杂的任务。
实施AI代理最困难的部分是组织的准备工作，而不是技术本身。
成功的AI代理实施需要五个阶段：准备评估、增量实施、基础技术建设、组织准备和路线图规划。
Salesforce的数据云和MuleSoft集成层对于Agent Force（Salesforce的代理式AI技术）至关重要。
实施AI代理需要新的角色，例如AI经理，专门负责管理AI代理。
AI技术发展迅速，需要持续的监控和更新，供应商应该提供持续的培训和支持。
AI代理需要持续监控和更新，因为其学习能力和推理能力会使其不断发展变化。
掌握提示工程是AI时代的一项重要技能，因为它影响着AI的输出结果。
多代理协作是AI代理发展的下一个阶段，它将涉及多个代理之间的协同工作，甚至可能跨越不同的公司。
企业需要采取负责任的方式来使用AI，包括定义护栏、进行风险评估和偏差测试。
分享了Starbucks的客户体验，认为其简单易用，并能够有效地结合人工和技术来提升客户体验。
Lauren Wood: 询问Irina Gutman解释预测性AI、生成式AI和代理式AI的区别。
supporting_evidences
Irina Gutman: 'Designing experience between an agent and a human is another flavor of a skill that is very new.'
Irina Gutman: 'When I talk to my innovation team, I'm constantly blown away. How they take capability of Salesforce AI product and turn it into the solution that elevates customer experience to a completely new level. I'm like, what? We can do that? This is not science fiction.'
Irina Gutman: 'Correct. Correct. You're absolutely correct.'
Irina Gutman: 'One of the examples of an agent, and we will talk further about different type of agent, but the funnest example that I can give is if you've been to Bay Area, they have VAMOS, which is the self-driverless car.'
Irina Gutman: 'And the thing about agentic AI that is just so incredible, which we're going to dive into so much more, but the thing about it that is so incredible is that it can think for itself.'
Irina Gutman: 'We refer to it as a reasoning engine, which kind of sort of an evolution of thing. One step further, it also has memory.'
Irina Gutman: 'Perfect. So let's keep in mind what we just learned about the genetic AI, right? Components of reasoning, memory, conversation, being able to infer action based on the information that's available to it and compare it to the chatbot.'
Irina Gutman: 'Absolutely. And by the way, yes, you are allowed to make spelling mistakes with agents, which is awesome.'
Irina Gutman: 'Agents have five components.'
Irina Gutman: 'Absolutely. And when I meet with customers, sometimes customer would tell me, give me an example of the sexiest, the most complex, advanced agent that you've ever built.'
Irina Gutman: 'But, and it's becoming more and more relevant with AI and agentic technology, turning on tech is the easiest part.'
Irina Gutman: 'If I could boil it down to the successful approach, I think we'll talk about five phases.'
Irina Gutman: 'From a Salesforce infrastructure perspective, and I'm going to talk about Salesforce, we have two key elements.'
Irina Gutman: 'I know people who are hiring AI managers, people whose role is just simply to manage the agents.'
Irina Gutman: 'Because sometimes the answer I provide you today might be obsolete and weaker too.'
Irina Gutman: 'What's foundational to all AI is how we interact with it.'
Irina Gutman: 'That is the most logical next evolution is that most of the companies even now have multiple agents.'
Irina Gutman: 'No, thank you for bringing it up. It is a very, very important topic.'
Irina Gutman: 'So I thought about that. I think I'm going to go with Starbucks.'
Lauren Wood: 'I want to make sure that everyone is caught up to what agentic AI is, because it is different from the generative AI and the predictive AI.'
Deep Dive
Shownotes Transcript