Day 2

This research introduces an agent-driven Text-to-SQL approach using fine-tuned Small Language Models (SLMs) and Retrieval-Augmented Generation (RAG) to simplify enterprise database interactions for non-technical users. It employs specialized agents for tasks like entity recognition, query decomposition, self-correction, and explainable results. Rolled out to 700 users in a pharmaceutical company, the system achieved 87% accuracy, reduced SQL effort by 70%, improved data access by 90%, and cut costs by 50%, enabling scalable, conversational self-service analytics for business users.

This research work addresses the critical challenge of on-shelf availability in retail, caused by delays, misplaced inventory, and phantom stock issues. It introduces a scalable AI-powered solution deployed across North American retailers, leveraging advanced ML models (e.g., ARIMA, XGBoost, neural networks) and distributed cloud processing. The system detects disruptions through an adaptive alert framework, enabling targeted resolutions and continuous improvement. Insights into inventory metrics support strategic interventions and mitigate upstream supply chain issues. This approach transforms inventory management, enhancing revenue and operational performance.

This research work presents an advanced solution to streamline the tendering process for engineers by automating Single Line Diagram (SLD) and technical specification processing. Traditional manual methods are inefficient and error-prone. The proposed system integrates OCR with a rule-based engine to extract critical SLD information, including component types and connections. Additionally, an LLM-based approach processes technical specifications, extracting data like requirements and compliance standards. This automation reduces manual effort, enhances accuracy, and accelerates tender responses, enabling engineers to prioritize strategic tasks.

This research work explores transitioning from third-party to in-house open-source OCR solutions to cut costs, improve data security, and enhance flexibility. The solution integrates barcode/QR code detection and supports 1D and 2D formats. It powers downstream applications like Retrieval-Augmented Generation (RAG) and text summarization, ensuring efficient processing. Standardized APIs reduce development time and integration complexity. Key strategies include framework selection, image optimization, and multilingual support. The approach improves cost-efficiency, privacy, and scalability while enabling advanced AI applications.

The presentation focuses on leveraging Generative AI (Gen AI) to drive transformative business strategies by aligning technology adoption with real-world applications. It highlights how Gen AI can address challenges such as content creation, customer engagement, product discovery, and operational inefficiencies, while emphasizing the importance of KPI-driven outcomes and actionable insights. The approach is human-centric, ensuring inclusivity through multilingual, multi-platform, and omni-channel support. By showcasing various case studies, the presentation demonstrates significant improvements in customer satisfaction, operational efficiency, and revenue generation. Ultimately, it underscores the potential of Gen AI to create value-driven, scalable solutions that enhance customer interactions and drive business growth.

GenAI is real. Business transformation using GenAI is also real. It is powerful and pervasive. But a disruptive technologies like GenAI cannot be devoid of issues and more so on biases and ethics. This session is to bring awareness on some of the biases and ethical issues.

In an era of global connectivity, organisations face the challenge of balancing scalability with compliance. This session explores how cloud computing and DevOps practices can help businesses establish a global presence while reducing operational costs and managing compliance in-house. Drawing on real-world examples, we’ll discuss how to eliminate the need for dedicated resources and optimise efficiency. Gain insights into leveraging cloud and DevOps to enhance global infrastructure while maintaining robust security and operational agility.

Developing generative AI-powered voice agents is typically a complex and time-consuming process, often taking weeks or even months. This session introduces a groundbreaking platform that shatters those barriers, enabling you to deploy sophisticated voice agents in just 24 hours. Discover how this revolutionary technology empowers you to rapidly create and customize intelligent voice experiences, transforming the way you interact with your customers.

Generative AI is transforming life insurance customer service by boosting efficiency and personalisation. From intelligent virtual assistants assisting customers 24*7 to seamless claims settlement process, AI is everywhere. It analyzes vast customer data to offer personalized policy recommendations, increasing satisfaction and loyalty. Additionally, Generative AI enhances risk assessment accuracy, simplifies underwriting processes, and produces engaging content. Despite challenges in regulatory compliance and data security, AI strengthens compliance measures and safeguards data, heralding a transformative impact on the industry.