Google patents system where AI agents plan and build digital content
Google describes a system where multiple AI agents work together to break down a user's goal into specific tasks. These agents prioritize the work, share information in a common memory, and use generative models to create and refine digital components like text or images.
In the filing’s own words
One example method includes obtaining, using one or more autonomous agents, user information; generating, using the one or more autonomous agents and based on the user information, a plurality of prompts; generating, using the one or more autonomous agents, as a plurality of candidate digital components, one or more candidate digital components for each prompt of the plurality of prompts; determining, using the one or more autonomous agents, digital component scores of the plurality of candidate digital components; determining, using the one or more autonomous agents and based on the digital component scores of the plurality of candidate digital components, at least one digital component of the plurality of candidate digital components; and generating, using the one or more autonomous agents, an output digital component including the at least one digital component.
What exactly they claim (claim 1)
1. A system comprising: one or more processors; and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to implement a multi-agent architecture comprising: a task creation agent configured to receive a user query indicating an objective and generate a plurality of tasks to achieve the objective, wherein the plurality of tasks includes at least a first task for generating a digital component; a task prioritization agent configured to analyze dependency relationships between the plurality of tasks, assign a priority level to each task of the plurality of tasks, and distribute the plurality of tasks into a plurality of task queues; a shared memory configured to store context data comprising task-result pairs associated with execution of the plurality of tasks; and an execution agent configured to: retrieve the first task from a selected queue of the plurality of task queues; query the shared memory to retrieve context data associated with the first task; execute the first task using a generative model to generate the digital component based on the retrieved context data; and store the generated digital component and a status of the first task in the shared memory as a new task-result pair accessible to the task creation agent or the task prioritization agent.
Facts
- Company
- Google (Google LLC)
- Official title
- AUTOMATING TASK GENERATION AND EXECUTION USING AUTONOMOUS AGENTS
- Publication number
- US20260270224A1
- Application number
- 19659664
- Filed
- Apr 27, 2026
- Published
- Sep 10, 2026
- Inventors
- 3
- Claims
- 20
Classified under
H04L 51/02 Electricity & electronicsMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.