Day 3

Witness a unique competition where a coder faces off against a non-coder armed with an AI tool like ChatGPT or Gemini. Who will win—human ingenuity or machine precision?

Kumar Varun is an Indian stand-up comedian, actor, writer and quizmaster. He is known for his roles in the comedy sketches of All India Bakchod, as the co-founder of the comedy collective Random Chikibum, which won the OML Comedy Hunt.

Deep networks are magical! But what is it about having multiple layers and billions of weights that leads them to doing this magic? In this talk, I will help you build intuition about how classical ML and deep learning differ, and why deep networks have taken over the world. We don’t yet have full theoretical understanding of why deep networks generalize well, but we have some hints. By the end of this talk, you’ll have a deeper appreciation about deep learning (maybe some pun intended!)

This research work presents a systematic approach to case deflection, enabling customers to resolve issues independently, reducing the need for support. It develops Intellectual Capital (IC) through analyzing documentation and engineer case notes, using a predictive model with supervised learning and NLP to classify bugs for digitization. The model prioritizes high-potential bugs, optimizing workflows and resource allocation. Large language models (LLMs) automate IC document creation, improving consistency and reducing manual effort. This AI-driven process enhances decision-making, customer satisfaction, and operational efficiency.

This research work introduces an autonomous large multimodal (LMM)-based agent for automating software and web operations using enterprise knowledge. The agent performs repetitive web tasks, automates decision-making, and enhances precision through retrieval-augmented generation (RAG). It leverages HTML parsing to create unique identifiers and integrates self-evaluation tools for task execution. Achieving 40% accuracy on open websites and higher on internal pages, it demonstrates a 24% improvement in precision. Key metrics include execution steps, token cost, and self-reflection capabilities.

This research introduces an LLM-based agentic framework aimed at reducing Mean Time to Recovery (MTTR) during IT incidents. The conversational AIOps Incident Management bot assists on-call personnel by recommending resources, referencing similar past incidents, and suggesting collaborators. It also automates tasks like generating post-incident reports and creating Jira issues for follow-up actions. The framework integrates root cause analysis, resolution guidance, and quality monitoring to enhance efficiency, user engagement, and overall incident management in complex IT service environments.

This research explores deep learning models to predict the aging and sudden death behavior of lithium-ion batteries (LIBs), critical for automotive energy systems. Traditional models struggle with LIB aging complexity, while DL models like LSTM, GRU, TCN, and Transformers effectively forecast capacity degradation and unexpected failures. Using data from 124 cells with diverse lifetimes, advanced data practices enhanced model accuracy. Metrics like RMSE and R² validated performance, highlighting DL’s potential in improving LIB management and automotive system reliability.

Data observability builds upon the principles of Infra/Software observability as well as practices of SRE to address nuanced challenges thrown in by modern data-driven systems. In this talk we explore the foundational concepts of Data observability and the landscape of multi-tenanted Data/AI products and additional requirements needed from observability. We delve into the specific challenges posed by multi-tenancy, including tenant-specific processing pipelines, usage patterns, data lineage, operational complexities, and the management of comprehensive data catalogs. Furthermore, we discuss the impact of evolving privacy regulations and compliance requirements, which underscore the necessity for robust, tenant-aware monitoring and auditing capabilities. Finally, we examine emerging trends, including AI-driven observability solutions, that are shaping the future of data reliability and scalability. These innovations aim to address the intricacies of multi-tenant environments while ensuring performance, transparency, and compliance at scale.