San Francisco, CA, United States of America

Paras Adhikary

This inventor holds 1 USPTO granted patent. Top assignee: Salesforce, Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Paras Adhikary. Retrieved from https://idiyas.com/inventor/paras-adhikary

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Paras Adhikary and Generative AI Planning

Introduction

Paras Adhikary is an inventor based in San Francisco, California. His patent work addresses how generative artificial intelligence systems can plan, produce, and validate outputs.

Latest Patents

Adhikary is associated with 1 patent: “Planning Phase and Generation Phase for Generative Artificial Intelligence.” The invention describes a system that receives a natural-language description of a desired output and uses one or more AI models to create multiple generation plans. The system ranks the plans, selects one, and follows its instructions to produce multiple outputs. It then ranks those outputs, selects a potential result, and validates it against parameters associated with the requested output.

Career Highlights

Adhikary works at Salesforce, Inc. His patent reflects an approach to generative AI that separates planning from generation and includes steps for ranking and validating results.

Collaborations

Adhikary’s listed coworker is Simone Mainardi. The available information identifies this workplace connection but does not specify a joint patent or other collaboration between them.

Conclusion

Paras Adhikary’s patent focuses on structuring generative AI workflows through plan selection, output ranking, and validation.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…