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

2025-06-25

AI Summary

Addressing the challenges of prompt authoring difficulty and strong dependency of system performance on prompt quality in domain-specific AI, this paper proposes a dynamic context-aware prompt recommendation method. Methodologically, it introduces a hierarchical skill knowledge base that integrates retrieval-augmented context grounding with behavior telemetry-driven adaptive skill ranking; additionally, it designs a two-stage reasoning mechanism enabling synergistic prompt synthesis via predefined templates and few-shot adaptive templates. Evaluated on real-world domain datasets, the approach demonstrates significant improvements—verified through both automated metrics and expert evaluation—including +28.6% gain in prompt relevance, as well as enhanced operationality and task completion rate. This work establishes a scalable technical pathway for high-accuracy, low-barrier domain-specific prompt engineering.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Improving prompt quality for domain-specific AI applications
• Dynamic context-aware prompt recommendation system development
• Enhancing relevance and usefulness of AI-generated prompts

Innovation

• Dynamic context-aware prompt recommendation system
• Retrieval-augmented knowledge grounding technique
• Two-stage hierarchical reasoning process