Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications
This addresses the problem of prompt quality for users of domain-specific AI applications, representing an incremental improvement through a novel method.
The paper tackles the challenge of crafting high-quality prompts for domain-specific LLM applications by developing a dynamic context-aware prompt recommendation system, which achieves high usefulness and relevance as validated by experiments on real-world datasets.
LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. Our solution combines contextual query analysis, retrieval-augmented knowledge grounding, hierarchical skill organization, and adaptive skill ranking to generate relevant and actionable prompt suggestions. The system leverages behavioral telemetry and a two-stage hierarchical reasoning process to dynamically select and rank relevant skills, and synthesizes prompts using both predefined and adaptive templates enhanced with few-shot learning. Experiments on real-world datasets demonstrate that our approach achieves high usefulness and relevance, as validated by both automated and expert evaluations.