Abstract
Configuring and optimizing artificial intelligence (AI) models for specific tasks can be a complex process that may involve deep technical expertise and iterative manual experimentation. This disclosure describes a system, which may be implemented as a self-improving AI agent, that can assist in automating this process by interpreting a user's intent to recommend a suitable AI model and configuration. The agent can analyze available models and propose settings, for example, system instructions, grounding data, and operational parameters. The system can also perform background evaluations to provide empirical data and a rationale for its recommendation. A human-in-the-loop component may be included to present proposed optimizations to a user for approval before the optimizations are implemented. This approach can aid in streamlining AI model optimization for a broader range of users, help align model behavior with user goals, and reduce the likelihood of unintended outcomes through controlled, human-validated improvements.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Glazier, Adam; Hawker, Colby; Sonoda, Jaime; and Rohde, Sönke, "System for Recommending AI Model Configurations with Human-in-the-Loop Oversight", Technical Disclosure Commons, (September 22, 2025)
https://www.tdcommons.org/dpubs_series/8608