The rise of AI Agents is transforming enterprise software architecture. Modern applications are no longer limited to static request-response systems - they are evolving into intelligent, autonomous, a...

Learn about your options for JavaFX, and what Oracle's change in support means for Java users.

: BellSoft survey finds 48% prefer pre‑hardened images over managing vulnerabilities themselves

In this critical episode, Ayan Gupta is joined by Rory who tackles one of the most important aspects of AI development: building responsibly. Just as you wouldn't want spilled coffee creating a mess, unchecked AI can have serious consequences. This session shows you how to put guardrails in place to ensure your AI applications are safe, fair, and trustworthy. Building on the techniques and applications, this episode demonstrates why responsible AI matters by first showing what happens when safety measures aren't in place. Using an unfiltered local model called Dolphin Mistral, Rory demonstrates how easily uncensored models can be manipulated to produce harmful content, highlighting the critical need for content filtering and safety measures. You'll then learn how GitHub Models and Azure AI provide multiple layers of protection. First, you'll explore how content safety filters create "hard blocks" that prevent harmful queries from even reaching the model, stopping violence, hate speech, and dangerous instructions before they're processed. Next, you'll see how AI models themselves are trained and red-teamed to "soft block" inappropriate requests, refusing to generate harmful content even when prompted. The session includes practical demonstrations of Azure AI Content Safety, showing you how to configure custom filtering thresholds for different categories like violence, hate speech, sexual content, and self-harm. You'll see real-time examples of both filtered and refused requests, and learn how to implement these protections in production applications like the Azure Search OpenAI Demo. Responsible AI isn't optional, it's essential. This session gives you the tools and knowledge to build AI applications that are both powerful and safe. Subscribe to continue learning best practices! Resources: https://aka.ms/JavaAndAIForBeginners https://aka.ms/genaijava 0:00 - Introduction: Why Responsible AI Matters 0:55 - Demonstration: Unfiltered AI Models 1:41 - The Problem with Dolphin Mistral 2:09 - Setting Up Your Codespace 2:42 - GitHub Models Content Safety Features 3:20 - Testing Harmful Content Filters 4:02 - Understanding Hard Blocks vs Soft Blocks 4:44 - Azure AI Content Safety Layers 5:29 - Configuring Custom Filter Thresholds 6:28 - Testing the Azure Search OpenAI Demo 7:21 - Throwing Exceptions for Critical Content 8:00 - Monitoring and Logging in Azure 8:40 - Session Recap: Production Best Practices 9:06 - Wrap-Up and Resources #ResponsibleAI #AIEthics #AzureAI #ContentSafety #AIGovernance #JavaDevelopment #SafeAI #AISecurity #GitHubModels #EthicalAI #AIFiltering

Resources: https://aka.ms/JavaAndAIForBeginners https://aka.ms/genaijava In this episode, Ayan Gupta is joined once again by Rory, who takes you on a deep dive into the core techniques that power generative AI applications. Building on the environment setup from Session "GenAI for Java Developers 1: Getting started", this session explores the different "brewing buttons" of GenAI, each one unlocking a completely different way to leverage AI in your Java applications. Think of it like a coffee machine with different buttons: espresso, cappuccino, latte. Each setting produces a unique result. Similarly, GenAI offers multiple techniques, completions, multi-turn chat, interactive chat, RAG (Retrieval Augmented Generation), and function calling—that enable you to build diverse AI-powered features. Rory demonstrates each technique hands-on using the GitHub Codespaces environment. You'll learn how to implement simple LLM completions for one-turn interactions, build multi-turn conversations that maintain context and history, create interactive chat applications that respond to user input in real-time, implement RAG to ground your AI responses in specific documents and prevent hallucinations, and use function calling to connect AI to business-critical operations like weather APIs and calculators. Each example includes practical code that you can run and modify yourself. By understanding these fundamental techniques, you'll have the building blocks to create sophisticated AI applications. This session builds directly toward the next session, where we'll put these techniques into practice by building three complete applications. Whether you're building chatbots, knowledge bases, or intelligent assistants, these techniques are essential. Subscribe and follow along as we continue this exciting journey! 0:00 - Introduction: Different Techniques, Different Results 0:50 - Setting Up the Code Space 1:04 - Technique 1: LLM Completions 1:50 - Testing Simple Completions 2:16 - Technique 2: Multi-Turn Chat 2:47 - Understanding Chat History and Context 3:30 - Technique 3: Interactive Chat 4:00 - Building a Real-Time Chat Interface 4:28 - Technique 4: RAG (Retrieval Augmented Generation) 5:14 - Grounding AI Responses in Documents 6:10 - Preventing Hallucinations with RAG 6:42 - Technique 5: Function Calling 7:25 - Building a Weather Function 7:52 - Creating a Calculator Function 8:36 - Session Recap: What We Covered 8:53 - Wrap-Up and Next Episode Preview #JavaTutorial #GenerativeAI #RAG #LLM #ChatGPT #FunctionCalling #AITechniques #JavaDevelopment #MachineLearning #OpenAI #GitHubModels