UiPath Releases a New Connector for Amazon Bedrock  

UiPath has introduced a new Integration - Service Connector - that enables UiPath customers to leverage Amazon Bedrock, a fully managed service offering access to cutting-edge foundation models (FMs) through an API. This will allow customers to easily create and expand generative AI applications, which is the company's focus, as seen with “Project Wingman,” its previous round of AI updates that allow customers to create powerful automation from simple natural language prompts.

“The UiPath connector for Amazon Bedrock is simple to use and brings the power of foundation models to all UiPath customers so they can accelerate building their own Generative AI applications. With its open, flexible, and responsible approach, UiPath provides organizations with a comprehensive platform for implementing and harnessing the power of AI-powered automation. This functionality complements our vision for helping customers innovate faster with Generative AI,” said Graham Sheldon, Chief Product Officer at UiPath.

UiPath's integration connector for Amazon Bedrock enables automation developers and citizen developers to seamlessly incorporate Generative AI directly into their UiPath Studio and Studio Web automation projects. This integration allows users to select their preferred model and operate within Amazon Web Services (AWS). The connector supports text and chat capabilities through Amazon Titan FMs and a range of other FMs from top AI providers available through Amazon Bedrock.

Additionally, the connector includes the Jurassic-2 family of multilingual large language models (LLMs) from AI21 Labs, which can generate text in multiple languages based on natural language instructions. Customers can also opt for Claude, an LLM developed by Anthropic, capable of performing various conversational and text processing tasks and known for its responsible AI system training research.

Generative AI relies on Foundation Models (FMs), which are exceptionally large models pre-trained on extensive datasets. According to AWS, these FMs can perform a wide array of tasks due to their extensive parameter count, enabling them to grasp intricate concepts. Through their pre-training process, FMs gain knowledge from the vast and diverse data found on the internet, allowing them to apply this knowledge effectively across various contexts.

Furthermore, it's important to note that all data remains encrypted and stays within the customer's Virtual Private Cloud (VPC). This means that customers can have confidence that their data will remain secure, private, and confidential.