Abstract
A common user interface for consumer use of generative artificial intelligence (genAI) tools is a chat interface, where a user can input their request as a text prompt within an input field and where the genAI model generates a response that answers the prompt. When users are insufficiently skilled at prompting, they may require multiple interactions with the genAI tool before a satisfactory result is generated. There are no mechanisms that guide the users to provide a prompt that uses good prompting strategies to express their intent. Also, user-provided prompts may include errors, gaps, or other issues that impact the generated response. This disclosure describes user interface techniques for providing users with assistance and guidance in identifying and rectifying a broad range of issues within their text prompt input before the text prompt is provided to a genAI model. Based on the automated feedback, the user can revise their prompt prior to requesting a response from the genAI model. This can reduce the need for tweaking of the prompt to obtain an appropriate response from the genAI model. By reducing the total number of prompts submitted to the AI model, the overall efficiency, effectiveness, time to satisfactory response, and ease of use in interactions with genAI models are improved.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Khan, Gulmohar; Sedouram, Ramprasad; and Srinivas, Karthik, "Real-time Feedback on User-written Generative Artificial Intelligence Model Prompts", Technical Disclosure Commons, (August 20, 2025)
https://www.tdcommons.org/dpubs_series/8490