UiPath Unveils New Family of LLMs at AI Summit to Empower Enterprises to Harness Full Capabilities of GenAI
UiPath announced several new generative AI (GenAI) features in its platform designed to help enterprises realise the full potential of AI with automation by accessing powerful, specialised AI models tailored to their challenges and most valuable use cases. UiPath showcased its latest capabilities at the virtual AI Summit that took place on March 19th, 2024.
The UiPath Business Automation Platform offers end-to-end automation for business processes. There are four key factors that business leaders seeking to embed AI in their automation program must keep top of mind: business context, AI model flexibility, actionability, and trust. The new AI features of the UiPath Platform address these key areas to ensure customers are equipped with the tools necessary to enhance the performance and accuracy of GenAI models and tools and more easily tackle diverse business challenges with AI and automation.
“Businesses need an assortment of AI models, the best in class for every task, to achieve their full potential. Our new family of UiPath LLMs, along with Context Grounding to optimise GenAI models with business specific data, provide accuracy, consistency, predictability, time to value, and empower customers to transform their business environments with the latest GenAI capabilities on the market,” said Graham Sheldon, Chief Product Officer at UiPath. “These new features ensure that AI has the integrations, data, context, and ability to take action in the enterprise with automation to meet our customers’ unique needs.”
At the AI Summit, UiPath announced:
Generative Large Language Models (LLMs)
The new LLMs, DocPATH and CommPATH, give businesses LLMs that are extensively trained for their specific tasks, document processing and communications. General-purpose GenAI models like GPT-4 struggle to match the performance and accuracy of models specially trained for a specific task. Instead of relying on imprecise and time-consuming prompt engineering, DocPATH and CommPATH provide businesses with extensive tools to customise AI models to their exact requirements, allowing them to understand any document and a huge variety of message types.
Context Grounding to augment GenAI models with business specific data
Businesses need a safe, reliable, low touch way to use their business data with AI models. To address this need, UiPath is introducing Context Grounding, a new feature within the UiPath AI Trust Layer that will be entering private preview in April. UiPath Context Grounding helps businesses improve the accuracy of GenAI models by providing prompts a foundation of business context through retrieval augmented generation. This system extracts information from company specific datasets, like a knowledge base or internal policies and procedures to create more accurate and insightful responses.
Context Grounding makes business data LLM-ready by converting it to an optimised format that can easily be indexed, searched, and injected into prompts to improve GenAI predictions. Context Grounding will enhance all UiPath Gen AI experiences in UiPath Autopilots, GenAI Activities, and intelligent document processing (IDP) products like Document Understanding.
GenAI Connectors & IBM watsonx.ai
IBM used UiPath Connector Builder to create a unique watsonx.ai connector. The new connector provides UiPath customers with access to multiple foundational models currently available in watsonx.ai. GenAI use cases, such as summarisation, Q&A, task classification, and optimisation for chat, are quickly integrated and infused into new and existing UiPath workflows and frameworks. IBM Watsonx customers can also access broader UiPath platform capabilities, such as Test Automation, Process Mining and Studio workflows, all within a low/no-code UX environment. IBM’s industry-leading consulting capabilities, coupled with the UiPath Business Automation Platform, will help support successful GenAI adoption, including the right strategy for infusing AI into more powerful, and complex automated workflows.
“IBM and UiPath strongly believe that AI and GenAI are rapidly changing the entire landscape of business globally,” said Tom Ivory, Senior Partner, Vice President, Global Leader of Global Automation IBM. “We are excited that IBM’s watsonx.ai and UiPath’s Connector Builder together now help create insights, efficiencies that result in real value for our customers.”
The IBM Watson Connector is now generally available through the Integration Service Connector Catalog.
Autopilot for Developers and Testers
UiPath Autopilot is a suite of GenAI-powered experiences across the platform that make automation builders and users more productive. Autopilot experiences for Developers and Testers are now available in preview with a targeted general availability in June. Over 1,500 organisations are using UiPath Autopilot resulting in over 7,000 generations and over 5500 expressions generated per week.
Autopilot for Developers empowers both professional and citisen automation developers to create automations, code, and expressions with natural language, accelerating every aspect of building automations.
Autopilot for Testers transforms the testing lifecycle, from planning to analysis, reducing the burden of manual testing and allowing enterprise testing teams to test more applications faster. Autopilot for Testers empowers testing teams to rapidly generate step-by-step test cases from requirements and any other source documents, generate automations from test steps, and surface insights from test results, allowing testers to identify root cause of issues in minutes, not hours or days.
Prebuilt GenAI Activities for faster time to value
New prebuilt GenAI Activities utilise the UiPath AI Trust Layer and are easy to access, develop with, and leverage high quality AI predictions in automation workflows that deliver faster time to value. GenAI Activities provides access to a growing collection of GenAI use cases, such as text completion for emails, categorisation, image detection, language translation, and the ability to filter out personally identifiable information (PII) enabling enterprises to do more with GenAI. With GenAI Activities, enterprises can reduce time to build and achieve a competitive edge using GenAI to help customise the customer experience, optimise supply chains, forecast demands, and make informed decisions.