Abstract
Existing approaches for interacting with specialized artificial intelligence (AI) agents often involve manual selection, leading to inefficient workflows, particularly for complex tasks that may require orchestration of multiple agents. This manual process can result in a fragmented and non-intuitive user experience. This document describes techniques that address this limitation by providing automated selection of specialized AI agents within an AI platform and orchestration of the selected agents to perform a complex task. This involves analyzing user prompts, classifying their intent, and intelligently suggesting or activating relevant custom agents. The selected agents then collaborate to address the user’s request. This approach enhances the usability of custom AI agents, can improve operational efficiency through seamless multi-agent collaboration, and offers a more intuitive and personalized user experience.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Prasad, Ajay, "Automated Selection and Orchestration of Custom AI Agents", Technical Disclosure Commons, (July 17, 2025)
https://www.tdcommons.org/dpubs_series/8372