PubMed is a free search interface for biomedical literature, including citations and abstracts from many life science scientific journals. It is maintained by the National Library of Medicine at the NIH. Yet, most users only interact with it through simple keyword searches. In this hands-on tutorial, we will introduce PubMed as a data source for intelligent biomedical research assistants — and build a Health Research AI Agent using modern agentic AI frameworks such as LangChain, LangGraph, and Model Context Protocol (MCP) with minimum hardware requirements and no key tokens. To ensure compatibility, the agent will run in a Docker container which will host all necessary elements.

Participants will learn how to connect language models to structured biomedical knowledge, design context-aware queries, and containerize the entire system using Docker for maximum portability. By the end, attendees will have a working prototype that can read and reason over PubMed abstracts, summarize findings according to a semantic similarity engine, and assist with literature exploration — all running locally on modest hardware.

Expected Audience: Enthusiasts, researchers, and data scientists interested in AI agents, biomedical text mining, or practical LLM integration. Prior Knowledge: Python and Docker familiarity; no biomedical background required. Minimum Hardware Requirements: 8GB RAM (+16GB recommended), 30GB disk space, Docker pre-installed. MacOS, Windows, Linux. Key Takeaway: How to build a lightweight, reproducible research agent that combines open biomedical data with modern agentic AI frameworks.

In this talk we’ll learn Infrastructure-as-Code by automating the world’s most popular game: Minecraft. Using Packer, Terraform and GitHub Actions, we’ll build a server, configure Linux, provision cloud infrastructure and operate it through GitOps. Finally, we’ll demonstrate how to go beyond automating traditional cloud control planes—automating the Minecraft world itself by using Terraform to build and demolish structures like castles and pyramids before our very eyes!

Join Red Hat’s Aaron Isom and Mark Heslin as they detail how Red Hat and Microsoft transformed into one of the most highly successful partnerships with over 10 years of collaboration in cloud computing and services. The session will highlight product offerings, benefits, future investments, and advancements, including OpenShift Virtualization, AI, Ansible and Red Hat Enterprise Linux (RHEL) specifically optimized for performance on Azure.

Learn how to seamlessly modernize a Linux application stack in Azure. Participants will be able to step through the migration process with a Linux/Postgres/Java application and utilize infrastructure as a code (IaC) for scale migrations.

Please RSVP and arrive at least 5 minutes before the start time, at which point remaining spaces are open to standby attendees.

Whether you use Ubuntu, RHEL, SLES, or Rocky, deploying Linux on Azure is more than provisioning VMs. Learn to build secure, performant Linux environments using Azure-native tools and partner integrations. See how to streamline image creation, harden workloads, monitor performance, and stay compliant with Azure Monitor, Defender for Linux, PostgreSQL on Azure, and the secure Linux baseline. Whether architect or OSS advocate, this session helps you confidently “train your penguin” for the cloud.

In this landmark 100th episode of Data Unchained, host Molly Presley sits down with Jonathan Flynn, Director of Applied Systems at Hammerspace, live from Supercomputing 2025. Together they explore the performance engineering breakthroughs that enabled Hammerspace and Samsung to deliver a historic IO500 10 Node Production result using only standard Linux, the upstream NFSv4.2 client, and off the shelf NVMe hardware. This episode breaks down how the Hammerspace Data Platform delivered more than a 33 percent gain over earlier submissions, doubled overall bandwidth, and achieved an unprecedented 809 percent improvement in the IO Hard Read test using Samsung PM1753 Gen 5 NVMe SSDs. Jonathan explains the Linux kernel innovations, metadata advancements, IO path optimization, parallel file system breakthroughs, and multi instance file placement strategies that allowed Hammerspace to reach genuine HPC class performance without proprietary clients or custom networking. Listeners get a detailed walkthrough of the architectural differences between Research and Production IO500 submissions, the impact of metadata redundancy, the performance benefits of NFSd direct and NFS direct, the role of ZFS locking improvements, and how upstream Linux contributions directly advanced the state of HPC and AI data infrastructure. Jonathan also highlights the evolution of MLPerf benchmarking, the benefits of tier zero storage, and how Hammerspace performance engineering is unlocking new levels of efficiency and scalability for AI training, scientific workloads, and large scale analytics. This episode is essential for AI architects, HPC engineers, kernel developers, data scientists, and infrastructure leaders building the next generation of high performance data platforms. Cyberpunk by jiglr | https://soundcloud.com/jiglrmusic Music promoted by https://www.free-stock-music.com Creative Commons Attribution 3.0 Unported License https://creativecommons.org/licenses/by/3.0/deed.en_US Hosted on Acast. See acast.com/privacy for more information.

Learn how to seamlessly modernize a Linux application stack in Azure. Participants will be able to step through the migration process with a Linux/Postgres/Java application and utilize infrastructure as a code (IaC) for scale migrations.

Please RSVP and arrive at least 5 minutes before the start time, at which point remaining spaces are open to standby attendees.

Learn how to seamlessly modernize a Linux application stack in Azure. Participants will be able to step through the migration process with a Linux/Postgres/Java application and utilize infrastructure as a code (IaC) for scale migrations.

Please RSVP and arrive at least 5 minutes before the start time, at which point remaining spaces are open to standby attendees.

Discover how to reduce your containerized application’s vulnerability footprint by leveraging the Azure Linux stack end-to-end. In this session, you’ll learn how to build distroless Azure Linux containers and deploy them on AKS nodes running Azure Linux. We’ll show you how this integrated approach minimizes CVEs, simplifies security management, and delivers a hardened environment for your workloads—all without sacrificing agility.

Azure Linux Container Host is an operating system image that's optimized for running container workloads on Azure Kubernetes Service (AKS). Learn how it improves performance, simplifies node lifecycle management, and enables innovations like pod sandboxing and OS Guard. See how customers use Azure Linux for workload isolation and hardened security with features like Integrity Policy Enforcement, SELinux, and dm-verity—helping enterprises modernize and scale with confidence.

Building secure applications in the cloud requires consistent governance and continuous compliance. Learn how to use Azure Policy to enforce organizational standards, remediate non-compliant resources, and maintain compliance at scale. We’ll also explore how Service Groups simplify security management by grouping and applying policies across applications, environments, and resource types. See how these innovations help you confidently secure Windows, Linux, and database workloads in Azure.

Delivered in a silent stage breakout.

DocumentDB, the open-source MongoDB-compatible document database now part of the Linux Foundation, helps you innovate faster and save more. Customers like Kraft Heinz move fast with a JSON-native model, reduce ops with turnkey scaling and updates, and secure workloads with enterprise-grade protection and an E2E Azure SLA. Delivered as a fully managed service with support for hybrid and multicloud, Azure DocumentDB keeps you moving faster while crushing costs at enterprise scale.

Azure brings unified management to on-premises and multi-cloud environments. Learn how Azure Arc delivers consistent governance, security, and operations across Azure, hybrid, and multi-cloud environments—while enabling System Center customers to adopt a cloud-native management experience. Whether modernizing Windows/Linux or building cloud-native apps, equip yourself with tools and agents to bridge datacenter and cloud.

Send us a text Dive into the powerful world of mainframes! Chief Product Officer of IBM Z and LinuxONE, Tina Tarquinio, reveals the truth behind those eight nines of uptime and explores how mainframes are evolving with AI, hybrid cloud, and future-proofing strategies for mission-critical business decisions. 

Discover the cutting-edge innovations transforming enterprise computing—from on-chip AIU and Spyre AI accelerators enabling real-time inferencing at transaction speed, to how LinuxONE is redefining hybrid cloud architecture.  Tina discusses DevOps integration, AI-powered code assistants revolutionizing mainframe development, compelling AI use cases, and shares her bold predictions for the mainframe’s next 100 years.  Plus, career advice from a tech leader and what she does for fun! 00:46 Tina Tarquinio03:18 The Most Mainframe Surprise09:12 What IS the Mainframe Really?  8 Nines!14:40 On Chip AIU, Spyre Inferencing18:11 Mainframes with Hybrid Cloud19:11 The Linux One Pitch19:59 Exciting Mainframe Innovations22:09 DevOps23:36 Code Assistants26:03 AI Use Case27:49 Future Proofing Decisions37:17 Regulations38:45 Bold Prediction38:58 Mainframe 10040:48 Career Advice42:24 For FunLinkedIn: linkedin.com/in/tina-tarquinio Website: https://www.ibm.com/products/z

MakingDataSimple #IBMz #Mainframe #LinuxONE #AIInferencing #SpyreAccelerator #HybridCloud #EnterpriseAI #DevOps #AICodeAssistant #EightNines #TinaTarquinio #MainframeModernization #AIUChip #FutureProofing #TechLeadership #WatsonxCodeAssistant #CloudComputing #TelumII

Want to be featured as a guest on Making Data Simple? Reach out to us at [email protected] and tell us why you should be next. The Making Data Simple Podcast is hosted by Al Martin, WW VP Technical Sales, IBM, where we explore trending technologies, business innovation, and leadership ... while keeping it simple & fun.

Discover how you can make the most of your IT estate migrations and modernizations with the newest AI capabilities. This session guides IT teams through assessing current environments, setting goals, and creating a business case with Azure Migrate for all of your workload types like Windows Server, SQL Server, .NET, Linux, PostgreSQL, Java, and more. We’ll explore tools to inventory workloads, map dependencies, and create actionable migration roadmaps.

Security standards often live in policy documents but aren’t consistently enforced. Learn how Azure Policy and Machine Configuration let you deploy built-in CIS benchmark templates for Linux and Windows, customize them to your needs, and apply them across Azure and hybrid / multi-cloud servers (via Azure Arc). We’ll also show how to integrate these policies into CI/CD pipelines (e.g., GitHub Actions) for continuous compliance checks, turning written guidelines into real-world security posture.

Want to ship applications faster? This demo shows you how to dramatically accelerate time to market with a high-velocity vibe coding workflow. We'll build a complete app with Azure Cosmos DB from scratch using GitHub Copilot as our AI pair programmer. We'll make use of the new Azure Cosmos DB Linux emulator and VS Code extension for local development to create a frictionless, end-to-end experience that helps you deliver features faster than ever before.

In this talk we’ll learn Infrastructure-as-Code by automating the world’s most popular game: Minecraft. Using Packer, Terraform and GitHub Actions, we’ll build a server, configure Linux, provision cloud infrastructure and operate it through GitOps. Finally, we’ll demonstrate how to go beyond automating traditional cloud control planes—automating the Minecraft world itself by using Terraform to build and demolish structures like castles and pyramids before our very eyes!

Discussion of the rapidly maturing RISC-V software ecosystem. Key projects such as Linux, GCC/LLVM, and OpenJDK are achieving significant milestones. Exploration of recent progress in performance-critical software, highlighting the impact of the RISC-V Vector extension and the RVA23 profile. Insight into how community efforts, including the RISE Project, are accelerating this collective work.