Akshay Mittal discusses the evolution of enterprise AI, focusing on the crucial shift from reactive to predictive security through AI-augmented DevSecOps. He explores how to productionize agentic AI workflows using AIOps and Kubernetes, and emphasizes the non-negotiable need for explainable AI (XAI) in critical systems.
Mem0 is building a model-neutral, persistent memory layer for AI agents to solve the fundamental statelessness of LLMs. Co-founders Taranjeet Singh and Deshraj Yadav discuss their hybrid memory architecture, which reduces cost and latency compared to context stuffing, and their vision for a future where user memory is portable across all AI applications.
Lior Gavish, CTO and co-founder of Monte Carlo Data, discusses the critical transition from data observability to agent observability. He covers the widespread adoption of AI agents in data teams, the new challenges they introduce for monitoring, and why traditional tools fall short in providing the necessary insights into agent performance, security, and governance.
Prashanth HN explores the powerful synergy between event-driven Agentic AI and Serverless architecture. Learn how AWS services like Lambda, Step Functions, and Bedrock provide the essential building blocks for creating sophisticated, scalable, and cost-effective AI agents, with practical examples of Agentic RAG, swarms, and orchestration patterns.
Zevi Arnovitz, a non-technical Product Manager at Meta, shares his complete workflow for building and shipping sophisticated applications using AI tools like Cursor. He details a structured, multi-step process that leverages different AI models for specific tasks, including a novel "peer review" technique where models critique each other's code.
Hitachi's Financial Business Unit developed a specialized LLM to automate the review of system design documents, addressing the inadequacy of general-purpose AI for mission-critical systems. This presentation details the model's development using Continued Pre-training and LoRA on proprietary data, its integration into a multi-agent architecture, and the use of Weights & Biases for MLOps, which led to a 70% reduction in manual review workload.