Agentic Engineering & ToolingConference50min
Why Java Is Perfect for AI - Just Not the AI You’re Thinking Of
The talk argues that enterprise AI should augment existing Java applications, not replace them. Java’s types, APIs, testing, and concurrency make it well suited to control unpredictable AI outputs, enabling fast, observable, dependable agentic systems without rebuilding architectures or surrendering core business processes.
talk.summaryAiDisclaimer
Trisha GeeDigital Aguacates
Andrey SantrosyanRedouble AI
Do you think AI belongs to Python? Are you worried we’re playing catch-up in the Java world? Don’t panic! Most enterprises aren’t training models or creating innovative AI tools. They’re adding AI capabilities to software they already run and trust.
Enterprise applications encode business processes, security rules, and decades of operational knowledge. Adding agents that attempt to rediscover a working process on every request is slower, more expensive, and less reliable than using AI where it is genuinely helpful: handling the uncertain and ambiguous parts of the workflow that used to need human intervention.
Java is especially strong for using AI. Java’s static types, mature APIs, testing tools, and explicit contracts provide structure around probabilistic (i.e. unpredictable) output. Its performance and concurrency model (including virtual threads) mean you can run large numbers of agentic tasks quickly and dependably. If your agentic framework works natively with Java, teams can add AI incrementally without rebuilding their architecture, retraining their engineers, or handing their core processes to an external black box.
In this talk, we'll look beyond chatbots and prompt engineering to see how AI actually fits inside enterprise applications, and how Java gives you the harness to make agentic systems fast, controlled, observable, and dependable.
Using AI effectively with Java in the enterprise isn’t some fantasy, it’s good, solid software engineering.
Enterprise applications encode business processes, security rules, and decades of operational knowledge. Adding agents that attempt to rediscover a working process on every request is slower, more expensive, and less reliable than using AI where it is genuinely helpful: handling the uncertain and ambiguous parts of the workflow that used to need human intervention.
Java is especially strong for using AI. Java’s static types, mature APIs, testing tools, and explicit contracts provide structure around probabilistic (i.e. unpredictable) output. Its performance and concurrency model (including virtual threads) mean you can run large numbers of agentic tasks quickly and dependably. If your agentic framework works natively with Java, teams can add AI incrementally without rebuilding their architecture, retraining their engineers, or handing their core processes to an external black box.
In this talk, we'll look beyond chatbots and prompt engineering to see how AI actually fits inside enterprise applications, and how Java gives you the harness to make agentic systems fast, controlled, observable, and dependable.
Using AI effectively with Java in the enterprise isn’t some fantasy, it’s good, solid software engineering.
Trisha Gee
Trisha Gee is a Java Champion, author, and internationally recognised speaker who has spent over 20 years building software and helping developers build it better. From high-performance financial systems to developer tools, she brings hands-on experience and a clear, practical perspective on what actually makes teams effective, and how engineering organisations build better software.
She is the co-author of Head First Java and Getting to Know IntelliJ IDEA, and her talks, articles, and videos are widely used by developers to navigate complex topics and improve how they work. She focuses on developer productivity, proven engineering practices, and the role of human judgment in an increasingly AI-assisted world.
Trisha got her start in developer communities, founding and supporting user groups and engaging directly with developers. She continues to champion community-led learning, inclusive practices, and the idea that great software comes from people, not just tools.
She is the co-author of Head First Java and Getting to Know IntelliJ IDEA, and her talks, articles, and videos are widely used by developers to navigate complex topics and improve how they work. She focuses on developer productivity, proven engineering practices, and the role of human judgment in an increasingly AI-assisted world.
Trisha got her start in developer communities, founding and supporting user groups and engaging directly with developers. She continues to champion community-led learning, inclusive practices, and the idea that great software comes from people, not just tools.