The News: Pegasystems announced on January 24 the Pega GenAI Knowledge Buddy, an enterprise-grade, generative AI-powered assistant that is designed to help customers and employees quickly retrieve specific answers synthesized by generative AI from content scattered across enterprise knowledge bases. According to the company, the Pega GenAI Knowledge Buddy combines an innovative AI architecture with security features so that organizations can transform how users access knowledge while adhering to high standards of trust and responsibility. Pega Knowledge Buddy will be available on Pega Cloud in the Pega Infinity ’24.1 release in H1 2024. You can read more about this announcement on Pegasystems’ website.
Pega Introduces New Generative AI Assistant
Analyst Take: Pegasystems announced an enterprise-grade, generative AI-powered assistant called Pega GenAI Knowledge Buddy that is designed to enable customers and employees to quickly and easily retrieve specific answers synthesized by generative AI from content scattered across enterprise knowledge bases. According to Pega, Knowledge Buddy is deployed within the Pega Cloud and utilizes retrieval augmented generation (RAG) architecture, which is designed to reduce or eliminate the risk of AI hallucination by restricting generative AI models to only answer based on the client’s content in their enterprise knowledge base. Compared with other approaches that require fine-tuning a private model, RAG allows more rapid evolution of content without the considerable ongoing cost and hallucination risk of fine-tuning.
Pega GenAI Knowledge Buddy’s Key Features and Functions
According to Pega, Knowledge Buddy will allow organizations to design simple, conversational interfaces that let customers or employees get specific, accurate, audited, and concise responses, while providing transparent attribution to sourced content. Users can also ask Knowledge Buddy to generate new content, such as emails or documents, based on their existing content libraries.
Organizations will be able to easily configure unique Buddies for different use cases—such as answering marketing, operations, sales, or service questions—and then quickly integrate them into any internal system or digital channel. Administrators have full control over the behavior and security of Buddies, and they can define and test AI-assistant prompts, guidelines, and access control.
Potential Use Cases and Scenarios
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:
- Marketing, where users can ask to get a concise summary of documented best practices, followed by a step-by-step process to create an offer.
- Operations, where users can ask a question and then receive an instant answer rather than search through compliance documents.
- Sales, where users can leverage existing content to draft a proposal rather than start from scratch.
- Service Buddy, where a customer wants to compare products, they can ask for the differences between two or more products via chat and then receive a concise summary instead of digging through website content.
To power these functions, Pega Knowledge Buddy 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 enables content versioning and lifecycle management, content templates, AI-generated content tagging, generative AI content generation suggestions, user feedback, usage reporting, and more.
Pega says that pre-built widgets for Pega applications such as Pega Customer Service 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. These are also going be available for customers. Similarly, customers will be able to embed Knowledge Buddy into existing websites and chatbots, extending the functionality of generative AI to customers and helping to improve inquiry deflection rates.
Providing Convenience While Ensuring Quality and Safety
Most important, Pega’s GenAI Knowledge Buddy is equipped with user controls to ensure a consistent quality of responses. Knowledge Buddy maintains a history of content updates so that users can understand what has changed over time. In addition, Answers generated by Buddies include clear citations back to an organization’s own content so that users can easily validate answers or drill deeper into content. Additionally, conversations are tracked and audited so that content managers can better report overall usage and gain insight into the types of questions being asked to fine-tune and improve Buddies over time.
Pega has also implemented role- and level-based content ownership controls, which are designed to help ensure only approved users can add or update specific content. Additionally, security features allow 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 workflow automation tools.
GenAI Buddy Focuses on Sure-Fire Use Cases
First, Pega should be commended for naming its generative AI-based assistant technology something other than copilot, as it serves as a clear differentiator from the many other vendors that are using a variation of the aerospace-themed moniker. But beyond the name, Pega appears to be taking a measured approach to providing its customers with a way to quickly generate ROI via its technology, focusing on customer- and employee-facing use cases that are a solid fit for using generative AI-powered assistants.
Because it uses RAG to ground the large language model (LLM) to a known and vetted source of data, the risks of hallucination should be low. Although it is incumbent upon end-user organizations to ensure that any data that will be used to ground a model is free from data that contains bias, toxicity, profanity, or other unwanted elements, RAG is an efficient technique to help ensure that models function as intended. Pega’s platform is designed to enable enterprises to quickly design and automate workflows, and its GenAI Knowledge Buddy appears to be a solid addition to its toolbox.
Disclosure: The Futurum Group is a research and advisory firm that engages or has engaged in research, analysis, and advisory services with many technology companies, including those mentioned in this article. The author does not hold any equity positions with any company mentioned in this article.
Analysis and opinions expressed herein are specific to the analyst individually and data and other information that might have been provided for validation, not those of The Futurum Group as a whole.
Other Insights from The Futurum Group:
Generative AI’s Current State, Challenges, and Industry Adoption
Pega Streamlines Chargeback Processes via Process AI
Author Information
Keith has over 25 years of experience in research, marketing, and consulting-based fields.
He has authored in-depth reports and market forecast studies covering artificial intelligence, biometrics, data analytics, robotics, high performance computing, and quantum computing, with a specific focus on the use of these technologies within large enterprise organizations and SMBs. He has also established strong working relationships with the international technology vendor community and is a frequent speaker at industry conferences and events.
In his career as a financial and technology journalist he has written for national and trade publications, including BusinessWeek, CNBC.com, Investment Dealers’ Digest, The Red Herring, The Communications of the ACM, and Mobile Computing & Communications, among others.
He is a member of the Association of Independent Information Professionals (AIIP).
Keith holds dual Bachelor of Arts degrees in Magazine Journalism and Sociology from Syracuse University.
