Supply chain operations generate vast amounts of operational data; however, critical knowledge such as system usage practices, troubleshooting workflows, and resolution techniques often remains buried within unstructured communications like support tickets, emails, and chat logs. While RAG systems aim to leverage such communications as a knowledge base, their effectiveness is limited by raw data challenges: support tickets are typically noisy, inconsistent, and incomplete, making direct retrieval suboptimal. Unlike existing RAG approaches that focus on runtime optimization, we introduce a novel offline-first methodology that transforms these communications into a structured knowledge base. Our key innovation is a LLMs-based multi-agent system orchestrating three specialized agents: Category Discovery for taxonomy creation, Categorization for ticket grouping, and Knowledge Synthesis for article generation. Applying our methodology to real-world support tickets with resolution notes and comments, our system creates a compact knowledge base - reducing total volume to just 3.4% of original ticket data while improving quality. Experiments demonstrate that our prebuilt knowledge base in RAG systems significantly outperforms traditional RAG implementations (48.74% vs. 38.60% helpful answers) and achieves a 77.4% reduction in unhelpful responses. By automating institutional knowledge capture that typically remains siloed in experts' heads, our solution translates to substantial operational efficiency: reducing support workload, accelerating resolution times, and creating self-improving systems that automatically resolve approximately 50% of future supply chain tickets. Our approach addresses a key gap in knowledge management by transforming transient communications into structured, reusable knowledge through intelligent offline processing rather than latency-inducing runtime architectures.

On February 8, 2023, Marc Benioff and Salesforce made a Twitter announcement about the teaser, giving a few cryptic hints about what to expect. Now that the official announcement has been made, the mystery surrounding Einstein GPT is slowly being cleared up. The first generative AI for CRM, Einstein GPT, was announced by Salesforce, the top provider of CRM software worldwide. This ground-breaking technology aids businesses of all sizes in automating procedures, boosting productivity, enhancing customer service and much more. By fusing NLP and machine learning, Einstein GPT can assist businesses in better understanding their clients, increasing sales, and improving marketing.

Salesforce is making a big deal this week of building OpenAI's GPT3 technology -- which powers ChatGPT -- into a broad swathe of its products, describing its Einstein GPT offering as "the world's first generative AI CRM technology." But as I explored in an interview published yesterday with Emergence Capital's Jake Saper, there are big risks in using these Large Language Models (LLMs) in a business context. I spent the day investigating whether Salesforce is cognizant of those risks, and what steps it is taking to ensure its customers don't fall foul of them when implementing solutions based on Einstein GPT. On the face of it, generative AI looks like it can bring a massive boost to business productivity, by making it easier to summarize information from unstructured data stored in documents, knowledgebases and message streams, preparing ready-made drafts for messages, emails and web content used in sales, service and marketing, or generating chunks of code and test routines for developers. But in more than twenty-five years of writing about and reporting on technology, I've seen enough to know that it's always sensible to look behind the hype and the enthusiastic demos to figure out what are the hidden downsides -- where could it all go wrong?

Customer behavior has experienced a whirlwind of changes due to the ongoing pandemic. And obstacles have never been lower while customers virtually connect with agents via phone, email, and texts. However, when it comes to interacting with business, points of friction are more numerous. Customers are often forced to deal with endless waits for an email response and companies often struggle to accommodate the limited availability of service desk agents during business hours. Moreover, service desk agents have soaring pressure to do more with less.

Objective: Medical relations are the core components of medical knowledge graphs that are needed for healthcare artificial intelligence. However, the requirement of expert annotation by conventional algorithm development processes creates a major bottleneck for mining new relations. In this paper, we present Hi-RES, a framework for high-throughput relation extraction algorithm development. We also show that combining knowledge articles with electronic health records (EHRs) significantly increases the classification accuracy. Methods: We use relation triplets obtained from structured databases and semistructured webpages to label sentences from target corpora as positive training samples. Two methods are also provided for creating improved negative samples by combining positive samples with na\"ive negative samples. We propose a common model that summarizes sentence information using large-scale pretrained language models and multi-instance attention, which then joins with the concept embeddings trained from the EHRs for relation prediction. Results: We apply the Hi-RES framework to develop classification algorithms for disorder-disorder relations and disorder-location relations. Millions of sentences are created as training data. Using pretrained language models and EHR-based embeddings individually provides considerable accuracy increases over those of previous models. Joining them together further tremendously increases the accuracy to 0.947 and 0.998 for the two sets of relations, respectively, which are 10-17 percentage points higher than those of previous models. Conclusion: Hi-RES is an efficient framework for achieving high-throughput and accurate relation extraction algorithm development.

The Cloudera Support Organization has always strived to not only provide solutions to our customers but to also deliver helpful knowledge. One of the primary sources of that knowledge comes from our Knowledge Articles. This content is created and curated by our knowledgeable Support Staff based on real-world experience coming from support cases. These Knowledge Articles have proven to be invaluable to our Support Staff over the years. While the content is also available to our customers to use in their own troubleshooting efforts, we want to do more to help bring the right Knowledge Articles to our customers at the right time.

The turnover rate for call center support agents is high. According to the 2016 U.S. Contact Center Decision Makers' Guide, the average term for a customer service representative is 3.3 years. Additionally, 60 percent of the turnover rate is from agents quitting. The highest turnover rate across all industries studied was found in outsourcers, aka third-party providers. No customer support job is easy, and call center agents are especially prone to emotional and physical burnout.