Burlingame, CA, United States of America

Eric Wang

This inventor holds 1 USPTO granted patent and 2 published patent applications. Top assignee: Dropbox, Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Eric Wang. Retrieved from https://idiyas.com/inventor/eric-wang-uak22p95

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

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Eric Wang: Inventor in Burlingame, California

Introduction

Eric Wang is an inventor based in Burlingame, California, and works at Dropbox, Inc. His patent work concerns using artificial intelligence models to improve the system prompts that guide agent models.

Latest Patents

Wang is associated with 1 patent: “Generating Modified System Prompts Associated with an Agent Model via a Meta-Prompting Model.” The invention describes a system in which an agent model generates an output in response to a task input, while a meta-prompting model compares that output with an expected result. Based on the differences, the meta-prompting model creates and may iteratively refine a modified system prompt. The system can store the improved prompt in a repository for later use with the agent model on a particular task.

Career Highlights

Wang’s listed patent reflects work on prompt optimization and the development of agent-based systems. By using comparisons between generated and expected outputs, the approach aims to help agent models produce results that better match task requirements.

Collaborations

Wang’s listed coworkers include Dmitriy Meyerzon and Hans Sayyadi. His professional affiliation is Dropbox, Inc.

Conclusion

Eric Wang’s patent describes a method for refining and reusing system prompts to improve agent-model outputs, highlighting his contribution to innovation in artificial intelligence systems.

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…