The primary objective was to improve response times for business-related queries and deliver a smooth, intelligent, and user-friendly search experience. To achieve this, the proposed solution focused on:

• Integrating multiple data sources
• Enabling real-time updates
• Leveraging AI technologies capable of producing accurate, context-rich results

At the time of assessment, the client’s data was fragmented across property listings, mall details, and app content, resulting in:

• Slow query performance
• Irrelevant search results
• Lack of contextual understanding
• Difficulty maintaining real-time synchronization without compromising scalability and security

The recommended solution was structured around three core pillars:

• Data Consolidation
• Intelligent Search Integration
• AI-Driven Query Processing

Key Recommendations

• Consolidate property, mall, and application data into Azure CosmosDB for structured storage and fast retrieval.
• Deploy an Enhanced Search Accelerator to serve real-time and historical data efficiently through optimized indexing.
• Use Azure API Management for secure integration across systems while retaining existing Snowflake and Oracle databases for compatibility and performance.
• Implement Large Language Models (LLMs) such as OpenAI, Llama or Claude for context-aware, natural responses.
• Utilize Azure Functions for real-time data updates and Azure Kubernetes Service (AKS) for scalability and reliability.

• Faster query response times
• Improved search relevance and personalization
• Seamless integration and real-time updates across systems
• Highly scalable, secure, and cloud-native architecture
• Enhanced customer satisfaction and engagement across platforms