US 12,298,880 B2
AI agent for pre-build configuration of cloud services
Rajeev Sudhakar Bhopi, Mercer Island, WA (US); Yiwen Zhu, San Francisco, CA (US); Helen Mary Serr, Boston, MA (US); Jonah Karpman, San Diego, CA (US); Matthew Joseph Gleeson, New York, NY (US); Nicholas Kent Glaze, Cambridge, MA (US); Subramaniam Venkatraman Krishnan, San Jose, CA (US); and Irwin Hollar McNeely, III, Cambridge, MA (US)
Assigned to Microsoft Technology Licensing, LLC., Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 13, 2023, as Appl. No. 18/487,024.
Prior Publication US 2025/0123939 A1, Apr. 17, 2025
Int. Cl. G06F 15/16 (2006.01); G06F 8/70 (2018.01); G06F 11/34 (2006.01)
CPC G06F 11/3442 (2013.01) [G06F 8/70 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processor; and
a computer-readable medium storing instructions that are operative upon execution by the processor to:
receive prior-existing utilization data and project metadata, wherein the utilization data comprises capacity information and resource consumption information for prior-existing computational resources, and wherein the project metadata includes information for hierarchically categorizing the prior-existing computational resources;
create, using the utilization data and project metadata, a capacity prediction model for generating a pre-build configuration for a first computational resource;
generate, using the capacity prediction model, the pre-build configuration for the first computational resource; and
tune the pre-build configuration using a selected cost and performance balance point and prior-existing project history data.