Patents by Inventor Jeffrey Ling

Jeffrey Ling has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20260329619
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that executes a software task utilizing an autonomous software agent. In particular, the disclosed systems receive a request to deploy an autonomous software agent, and the disclosed systems provide access to a shell and an integrated development environment. Moreover, the disclosed systems, execute, by the autonomous software agent, the software task responsive to the request based on utilizing the shell and the integrated development environment.
    Type: Application
    Filed: July 2, 2026
    Publication date: October 22, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Moritz Stephan, Silas Alberti, Gennady Korotkevich
  • Publication number: 20260277653
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that executes a software task utilizing an autonomous software agent. In particular, the disclosed systems receive a request to deploy an autonomous software agent, and the disclosed systems provide access to a shell and an integrated development environment. Moreover, the disclosed systems, execute, by the autonomous software agent, the software task responsive to the request based on utilizing the shell and the integrated development environment.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Moritz Stephan, Silas Alberti, Gennady Korotkevich
  • Publication number: 20260277668
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that deploys an autonomous software agent to generate artificial intelligence outputs responsive to the software task based on accessing the one or more code repositories. In particular, the disclosed systems connect an autonomous software agent system with a computer code repository management system. Moreover, the disclosed systems receive a prompt to deploy an autonomous software agent, and the disclosed systems deploy the autonomous software agent within an independent virtual machine computing environment to execute a software task by accessing one or more connected code repositories. Additionally, the disclosed systems generate artificial intelligence outputs based on accessing the connected code repositories.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling
  • Publication number: 20260277646
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that deploys an autonomous software agent and displays actions taken by the autonomous software agent on a graphical user interface on a user computing device. In particular, the disclosed systems provide an interactive browser of an independent virtual machine computing environment of the autonomous software agent for display within a graphical user interface. Moreover, the disclosed systems provide an application running on the independent virtual machine computing environment for display in the interactive browser.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Moritz Stephan, Silas Alberti, Gennady Korotkevich
  • Publication number: 20260278165
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that deploys an autonomous software agent and determines an activation trigger that indicates an access credential as part of completing a software task. In particular, the disclosed systems receive a prompt to execute a software task and determine (e.g., via an autonomous software agent) an activation trigger that indicates an access credential is required as part of completing the software task. Moreover, the disclosed systems make a call for a token corresponding to the access credential based on the activation trigger. Furthermore, the disclosed systems receive the token in an independent virtual machine computing environment and use the token to complete the software task.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling
  • Publication number: 20260277578
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that connects with a messaging application for digital conversations between a plurality of users and deploys an autonomous software agent via a prompt received from the messaging application. In particular, the disclosed systems connect a messaging application with an autonomous software agent system. Moreover, the disclosed systems receive a prompt to activate an autonomous software agent from the messaging application. Additionally, the disclosed systems deploy the autonomous software agent that operates within an independent virtual machine computing environment to generate artificial intelligence outputs responsive to the prompt and proves the artificial intelligence outputs to the messaging application.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Moritz Stephan
  • Publication number: 20260277654
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that deploys an autonomous software agent and accesses a virtual machine snapshot. In particular, the disclosed systems receive a request to deploy an autonomous software agent, and the disclosed systems access a virtual machine snapshot, where the virtual machine snapshot is a custom software development environment comprising at least one of access to a code repository, access to one or more functional tools, or access to one or more code dependency libraries. Moreover, the disclosed systems execute the software task by using the autonomous software agent to perform one or more actions within the custom software development environment.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Carlo Baronio, Gennady Korotkevich
  • Publication number: 20260277579
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that deploys an autonomous software agent to execute a software task responsive to a system prompt. In particular, the disclosed systems provide a playbook library that includes a plurality of reusable system prompts. Moreover, the disclosed systems receive a system prompt selected from the plurality of reusable system prompts. Additionally, the disclosed systems deploys an autonomous software agent, which operates within an independent virtual machine computing environment, to execute a software task responsive to the system prompt selected from the playbook library.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling, Moritz Stephan
  • Publication number: 20260278408
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that provide an autonomous software agent with relevant knowledge items to execute a software task. In particular, the disclosed systems provide a knowledge creation option to create software composition instructions for an independent virtual machine computing environment to reference across different development sessions. Moreover, the disclosed systems receive knowledge items pertaining to a knowledge trigger and further receive a prompt to deploy an autonomous software agent within the independent virtual machine computing environment. Additionally, the disclosed systems determine that the software task indicates a knowledge trigger and provide the knowledge items to the autonomous software agent to aid in executing the software task.
    Type: Application
    Filed: March 9, 2026
    Publication date: September 17, 2026
    Inventors: Tony Jiang, Scott Wu, Steven Hao, Sampriti Panda, Walden Yan, Adhyyan Sekhsaria, Jeffrey Ling
  • Publication number: 20260212162
    Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.
    Type: Application
    Filed: March 16, 2026
    Publication date: July 23, 2026
    Inventors: Jonathon Shlens, Vijay Vasudevan, Jiquan Ngiam, Benjamin James Caine, Zhengdong Zhang, Zhifeng Chen, Hao-Tien Chiang, David Joseph Weiss, Jeffrey Ling, Ashish Venugopal
  • Patent number: 12626106
    Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: May 12, 2026
    Assignee: Google LLC
    Inventors: Jonathon Shlens, Vijay Vasudevan, Jiquan Ngiam, Benjamin James Caine, Zhengdong Zhang, Zhifeng Chen, Hao-Tien Chiang, David Joseph Weiss, Jeffrey Ling, Ashish Venugopal
  • Patent number: 12030523
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment.
    Type: Grant
    Filed: August 6, 2021
    Date of Patent: July 9, 2024
    Assignee: Waymo LLC
    Inventors: David Joseph Weiss, Jeffrey Ling
  • Publication number: 20230041501
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network. In one aspect, a method for training a policy neural network configured to receive a scene data input and to generate a policy output to be followed by a target agent comprises: maintaining a set of training data, the set of training data comprising (i) training scene inputs and (ii) respective target policy outputs; at each training iteration: generating additional training scene inputs; generating a respective target policy output for each additional training scene input using a trained expert policy neural network that has been trained to receive an expert scene data input comprising (i) data characterizing the current scene and (ii) data characterizing a future state of the target agent; updating the set of training data; and training the policy neural network on the updated set of training data.
    Type: Application
    Filed: August 6, 2021
    Publication date: February 9, 2023
    Inventors: David Joseph Weiss, Jeffrey Ling, Adam Edward Bloniarz, Cole Gulino
  • Publication number: 20230040006
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for planning the future trajectory of an autonomous vehicle in an environment.
    Type: Application
    Filed: August 6, 2021
    Publication date: February 9, 2023
    Inventors: David Joseph Weiss, Jeffrey Ling
  • Publication number: 20220383076
    Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.
    Type: Application
    Filed: May 31, 2022
    Publication date: December 1, 2022
    Inventors: Jonathon Shlens, Vijay Vasudevan, Jiquan Ngiam, Benjamin James Caine, Zhengdong Zhang, Zhifeng Chen, Hao-Tien Chiang, David Joseph Weiss, Jeffrey Ling, Ashish Venugopal