US 12,463,863 B1
Agentically-orchestrated foundational models for cloud architecture design
Aayush Srivastava, New York, NY (US); Alison Marlene Andrews, Stonington, CT (US); and Priyanka Vergadia, San Jose, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 1, 2024, as Appl. No. 18/651,866.
Int. Cl. H04L 41/0803 (2022.01); H04L 67/10 (2022.01)
CPC H04L 41/0803 (2013.01) [H04L 67/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, by a computing system comprising one or more computing devices, a set of inputs comprising:
user response information comprising information indicative of cloud architecture requirements for a cloud architecture to fulfill; and
proposed architecture information indicative of a proposed cloud architecture comprising a plurality of proposed generic component placeholders for components necessary to meet the cloud architecture requirements;
processing, by the computing system, the set of inputs with a plurality of agentic orchestration models to obtain a role output comprising component selection information indicative of a plurality of cloud components selected for the plurality of proposed generic component placeholders, wherein, for each of the plurality of proposed generic component placeholders, the component selection information selects a particular cloud component from a set of candidate cloud components, and wherein each of the plurality of agentic orchestration models comprises a machine-learned model prompted to fulfill a corresponding cloud architecting role of a plurality of cloud architecting roles; and
based on the component selection information, providing, by the computing system, information indicative of the plurality of cloud components selected for the plurality of proposed generic component placeholders to a user device associated with the user response information.