{"id":11591,"date":"2024-12-17T11:00:00","date_gmt":"2024-12-17T19:00:00","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=11591"},"modified":"2024-12-18T07:39:44","modified_gmt":"2024-12-17T20:39:44","slug":"reasoning-engine-for-ai-agents","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/au\/news\/stories\/reasoning-engine-for-ai-agents\/","title":{"rendered":"How an Advanced Reasoning Engine Is Powering the Next Generation of AI Agents"},"content":{"rendered":"\n

Every AI agent<\/a> needs reasoning abilities. It\u2019s what gives them the ability to analyze, adapt, and make meaningful decisions. But until Salesforce\u2019s Agentforce<\/a> came along, no AI agents, copilots, or assistants had a true, enterprise-class reasoning en<\/a>gine<\/a> for transforming raw data and metadata into intelligent actions that mimic or even surpass human thinking.<\/p>\n\n\n\n

“Reasoning engines combine models, data, business logic, events, and workflows into unified cognitive architectures,” said Phil Mui, Ph.D., SVP of Technology, Head of Products and Engineering, Salesforce AI Research and Agentforce. “Reasoning engines are compound systems. The good ones are fast inference time System 2 reasoners. They try to understand the nuances of user queries, contexts and provide accurate, faithful, and sometimes actionable responses.”<\/p>\n\n\n\n

\n

Reasoning engines combine models, data, business logic, events, and workflows into unified cognitive architectures.<\/p>\nPhil Mui, Ph.D., SVP of Technology, Head of Products and Engineering for Salesforce AI Research<\/cite><\/blockquote>\n\n\n\n

This is a striking shift from the AI assistants we\u2019ve come to know, with their scripted prompts and unpredictable replies. Inspired by noted psychologist Daniel Kahneman\u2019s bestseller, Thinking, Fast and Slow<\/em><\/a>,<\/em> reasoning engines integrate the dual-process framework of human thought \u2014 the idea that we can sometimes be quick to react in a moment because a situation calls for it. Or we can take a moment, think about things more deeply,  and come up with more intricate solutions to problems or needs. <\/p>\n\n\n\n

In AI<\/a> terms, many do-it-yourself (DIY) assistants, which are essentially thin software veneers over large language models (LLMs)<\/a>, go down that first rapid, or \u201cSystem 1\u201d path because they\u2019re built for basic tasks like answering frequently asked questions or taking product orders. But organizations thinking about employing agents to offload or augment human work need higher levels of reasoning. This is where \u201cSystem 2\u201d inference comes into play with its ability to understand and think through a situation, deliver relevant insights, and suggest actions.<\/p>\n\n\n\n