India – January 25, 2024 – Pegasystems Inc. (NASDAQ: PEGA), the leading enterprise AI decisioning and workflow automation platform provider, today announced Pega GenAI Knowledge BuddyTM, an enterprise-grade, generative AI-powered assistant that will quickly and easily enable customers and employees to get specific answers synthesized by generative AI from content scattered across enterprise knowledge bases. Pega GenAI Knowledge Buddy uniquely combines an innovative AI architecture with security features so organizations can transform how users access knowledge while adhering to high standards of trust and responsibility.
Enterprise knowledge content is frequently too hard to find, too complicated to understand, and too disconnected from employee and customer workflows to be useful. Information is stored within lengthy, dense documents that are fragmented across dozens of disconnected systems, leaving employees to repeatedly search to piece together the information they need to do their jobs. This also impacts customers who can’t quickly get answers using self-service channels, leading to collective frustration for all users. Generative AI bots can help in theory, but most tend to be consumer-grade products that lack the critical features enterprises need to work securely and effectively, or code-based “science projects” that are far too brittle to handle the constant flux and change in an enterprise content library.
Pega GenAI Knowledge Buddy will offer enterprises an alternative. With Knowledge Buddy, customers and employees can ask questions through simple, conversational interfaces and get specific, accurate, audited, and concise responses – with transparent attribution to source content. Knowledge Buddy will automatically search, analyze, and synthesize existing document libraries to quickly generate answers. Users can also ask Knowledge Buddy to generate new content, such as emails or documents, based on their existing libraries. Additionally, security features give organizations control over user access rights as well as transparency to understand how and from where the technology pulls information. Content authors will be able to easily add, update, or delete knowledge, with all actions managed and audited by Pega’s industry-leading workflow automation.
Organizations will be able to easily configure unique Buddies for different use cases – such as answering marketing, operations, sales, or service questions – and quickly integrate them into any internal system or digital channel. The results: more productive employees, more satisfied customers, and more effective overall operations.
Pega GenAI Knowledge Buddy will help organizations securely unlock the full power of their knowledge bases with features that enable them to:
· Quickly and securely configure and test AI-powered assistants: Administrators will have full control over the behavior and security of their Buddies. Through a simple configuration experience, they can define and test AI-assistant prompts, guidelines, and access control. Existing content libraries are quickly imported with standard APIs. Pega’s enterprise-grade security and governance capabilities enable organizations to define role-based visibility across content bases to help ensure users have access to the appropriate information.
· Use controls to ensure quality content and user access: Knowledge Buddy maintains a history of content updates so users can understand what’s changed over time. Additionally, fine-grained controls over content ownership help ensure only approved users can add or update specific content, maintaining better version control and quality content sources.
· Leverage generative AI-powered Q&A for better accuracy and transparency: For each Buddy configured, Pega GenAITM automatically enables an intelligent Q&A experience using a state-of-the-art Retrieval Augmented Generation (RAG) architecture. RAG minimizes the risk of AI hallucination by restricting GenAI models to only answer based on the client’s content in their enterprise knowledge base. Compared to other approaches that require ‘fine tuning’ a private model, this allows more rapid evolution of content without the considerable ongoing cost and hallucination risk of fine tuning. Knowledge Buddy is deployed on the certified Pega CloudTM architecture, so administrators and developers can focus on optimizing the user experience – not coding the infrastructure.
· Ensure better auditability with more transparent processes: Answers generated by Buddies include clear citations back to an organization’s own content so users can easily validate answers or drill deeper into content. Additionally, conversations are tracked and audited so content managers can better report overall usage and gain insight into the types of questions being asked to fine-tune Buddies over time.
· Connect AI-powered assistants into service and operations apps: Pre-built widgets for Pega applications such as Pega Customer Service TM and a set of auto-generated APIs let developers plug different Buddies directly into any channel or front end for easy activation across their employee and customer population.
· Plug AI-powered assistants into customer-facing websites: Enterprises can optimize their self-service experiences by embedding Knowledge Buddy into existing websites and chatbots. This enables customers to get answers quickly and more accurately without escalating to an agent.
With Pega GenAI Knowledge Buddy’s flexible foundation for rapid deployment of generative AI-powered knowledge assistants, organizations can create their own customized Buddies for a variety of scenarios, such as:
· “Marketing Buddy:” When a marketer needs to create a new customer offer, they can ask, “What’s the best way to create a new retention offer?” to get a concise summary of documented best practices, followed by a step-by-step process to create the offer.
· “Operations Buddy:” When assessing how to process a transaction dispute in a new region, a banking operations employee can ask, “What are the details of the regulations that apply to this region?” and receive an instant answer rather than searching through compliance documents.
· “Sales Buddy:” When putting together a proposal for a prospect, a sales rep can say, “Draft me a proposal for our enterprise offering that would resonate with an executive,” to receive a near-final proposal rather than starting from scratch.
· “Service Buddy:” When a mobile phone customer wants to compare the terms of different plans, they can ask via chat, “What are the differences between each cell phone plan?” to get a concise summary instead of digging through website content.
Pega Knowledge Buddy also connects to knowledge libraries within Pega Knowledge Management, which allows organizations to build, manage, and optimize content by assisting content authors and managers during the curation process. Pega Knowledge Management enables content versioning and lifecycle management, content templates, AI-generated content tagging, generative AI content generation suggestions, user feedback, usage reporting, and more.
Pega Knowledge Buddy is the latest generative AI-powered capability in the Pega InfinityTM portfolio of products, building on over 20+ new capabilities in Pega GenAI. It will be available on Pega Cloud in the Pega Infinity ’24.1 release in H1 2024.
Quotes & Commentary:
“Organizations want to use AI to improve experiences and increase efficiency, but many existing solutions aren’t meant for the intricate inner workings and complex needs of large organizations. And while many want to use generative AI to do the heavy lifting when seeking answers within massive content libraries, they also need security, transparency, and auditability to use the technology with confidence,” said Kerim Akgonul, chief product officer, Pega. “Pega Knowledge Buddy will unlock new levels of productivity with enterprise-grade generative AI capabilities that seamlessly and securely integrate into these content libraries so both employees and customers can quickly get optimal answers and guidance with more accuracy, easily resolve service issues, and provide smoother experiences for all users.”