Code Conversations

Are massive context windows replacing RAG? 🤔 Martin Keen breaks down RAG vs. long context in LLM workflows. Explore how vector databases, semantic search, and embedding models impact AI performance to help you choose the right solution for your applications. 🚀

AI agents are having a moment, and understanding MCP and ADK is key to building them well. Cedric Clyburn and Anna Gutowska explain how MCP powers tool integration while ADK structures reliable multi‑agent systems 🤖. Learn when to use each to build more capable and predictable AI agents.

Ready to become a certified GenAI engineer? Register now and use code IBMTechYT20 for 20% off of your exam → https://ibm.biz/BdGhCFLearn about the technology → https://ibm.biz/BdMsRTLarge language models usually give great answers, but because they're limited to the training data used to create the model. Over time they can become incomplete--or worse, generate answers that are just plain wrong. One way of improving the LLM results is called "retrieval-augmented generation" or RAG. In this video, IBM Senior Research Scientist Marina Danilevsky explains the LLM/RAG framework and how this combination delivers two big advantages, namely: the model gets the most up-to-date and trustworthy facts, and you can see where the model got its info, lending more credibility to what it generates.

Ref: https://www.youtube.com/watch?v=T-D1OfcDW1M

MCP or API: Which transforms AI integration? Martin Keen explains how the Model Context Protocol (MCP) revolutionizes AI agents by enabling dynamic discovery, tool execution, and seamless external data retrieval. Discover how MCP simplifies LLM workflows and outpaces traditional APIs.

Ref: https://www.youtube.com/watch?v=7j1t3UZA1TY

Tim Berglund is back at the lightboard with MCP (Model Context Protocol). MCP really is a big deal, but most people are missing the point. It's not just about enhancing desktop applications with agentic functionality—it's about exposing reusable tools and resources (including real-time data from sources like Apache Kafka) to build agentic microservices. Doing this takes us beyond basic LLM chatbots to dynamic, problem-solving systems that deliver real value in real professional settings.

With the rise of AI and automation, how do we as humans find our value in the workplace? How do we work with these new technologies? How do we build resilience to changes? What skills are needed for us to thrive in this new world?People have often felt apprehensive about change, especially big changes to the way we work. It happened in the industrial revolution and now it's happening with the rise of artificial intelligence. Five years ago these things existed, but now they are accessible to almost everyone.

Ref: https://www.youtube.com/watch?v=IJjl4X1Lr8w

Learn how AI can change the game in an important scenario. The age-old battle between Product Owners and Developers rages on: POs push for speed, while devs demand clarity. When specs are too vague, developers waste time making assumptions. When specs are too detailed, POs get bogged down in documentation.The result? Context switching, frustration, and a backlog filled with half-baked work items.In this talk, Adam Cogan will show how AI powered tools like YakShaver (for GitHub and Azure DevOps) and recently Loom (for Jira) can act as the ultimate peacemaker.These tools capture discussions, structuring work items, and ensuring that every backlog item is ready… and assigned to the right backlog—all automatically.

Ref: https://www.youtube.com/watch?v=u_JSpT3i1Z4&list=TLGGLRPrrPRtEmAyMDAzMjAyNg

Copilots are everywhere these days, and… rightfully so! Let's face it: these tools are incredible at getting things done. They have the potential to turn any one of us into a 20x developer. Need a new feature? Bam, there you have it! Refactor that function? Sure, it'll be done before you grind the coffee for your next cup. These tools do a very good job of generating well-designed, tested, and performant code. Before you know it, you're not just building a feature—you're building 17 slightly different features simultaneously because why not? After all, the code writes itself!But guess what? Just because you can build it doesn't mean you should. Without a clear vision, our solutions risk becoming soulless Franken-software, a mishmash of best intentions and uncontrolled enthusiasm that don't make the user's life any easier. That’s why we need to remind ourselves that the true art of building great systems is more about what you choose not to do. More than ever, our mission needs to remain crystal clear: crafting lasting, impactful solutions that our users love.

Ref: https://youtu.be/6UGgP8l7TA4?list=TLGGCR2Fp6AOZlMxNDAzMjAyNg

Explore how AI and continual learning can revolutionize MRI diagnostics, using our real-world case study in detecting Focal Cortical Dysplasias (FCD)—a crucial factor in epilepsy treatment. In this session, we’ll dive into how continual learning techniques, inspired by human adaptability, help AI models improve diagnostic accuracy, minimize false positives, and handle evolving data in medical settings. We’ll discuss challenges like catastrophic forgetting, maintaining model performance in dynamic environments, and practical strategies that developers can apply to other domains. Gain hands-on insights into building resilient AI systems that evolve and adapt to new data, ensuring long-term reliability in critical applications.

Ref: https://www.youtube.com/watch?v=WsHfnJLXP-U&list=TLGGrM3vbzrnOnoxNDAzMjAyNg

Ready to give your old code a makeover? Step into the world of AI-powered code refactoring, where smart algorithms take on the challenge of sprucing up cluttered codebases. See how AI deciphers code DNA, performs digital reconstructive surgery, and scales from small scripts to sprawling systems. Explore real-world success stories, understand the current limits, and discover tools that'll make your development process smoother than a freshly refactored function.

Ref: https://www.youtube.com/watch?v=u8tvVxUOwvY&list=TLGGNgLFYxiYuL8xNDAzMjAyNg