Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

TL;DR

This paper introduces a dynamic, context-aware prompt recommendation system for domain-specific AI applications, enhancing prompt relevance and quality through hierarchical reasoning, knowledge grounding, and adaptive templates.

Contribution

It proposes a novel system combining contextual analysis, hierarchical skill organization, and adaptive prompt synthesis for improved domain-specific prompt recommendations.

Findings

Achieves high relevance and usefulness in real-world datasets

Validated by automated and expert evaluations

Outperforms baseline prompt recommendation methods

Abstract

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.