Amazon Technologies, Inc.

Brijesh Luckria

Abhijit S Barde

Rashmi Gangadharaiah

Deepak Seetharam Nadig

Sopan Khosla

Fawad Abbas

Bhaskar Hosahalli Rangaswamy

Siddharth Satish Goyal

Erik Nathaniel Haukenes

Karanpaul Singh Chawla

Bhaskar Hosahalli Hosahalli Rangaswamy

Michael W Miller

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

Processing natural language queries for network-based services

Techniques for a system to automatically recommend supported actions to a notification associated with a resource in a cloud computing environment are discussed herein. A system can includes a recommendation engine and a registry to provide centralized management of actions for responding to a notification instead of each service managing actions separately. A machine learned model can generate recommendations for resolving the notification based on a template stored in the registry that associates actions with instructions for presenting the recommendation in a respective interface modality (e.g., Chatbot, mobile application, console, etc.). In some examples, the system can implement a machine learned model, a graph model, and/or a heuristic model, to determine potential actions as recommendation data.

Multi-modal recommendation system in a cloud computing environment

Growing community of inventors

Fayetteville, NC, United States of America

Brijesh Luckria