Enterprise AI Engineering

Designing the Next Generation of AI-Native Systems

🇬🇧 English

Build AI-Native Enterprise Systems That Scale

Artificial Intelligence is rapidly becoming a core component of modern enterprise architectures. From agentic workflows and RAG systems to MCP-powered integrations and intelligent automation, AI is no longer limited to chatbots or coding assistants. Organizations now need architectures, platforms, and governance models that enable AI to operate reliably, securely, and at scale.

In this course, you’ll learn how AI is reshaping software engineering, platform engineering, operations, and product development. Through practical sessions and real-world examples, you’ll explore the technologies, patterns, and organizational changes required to build production-ready AI-native systems.

From AI Experiments to Enterprise Engineering

Successfully adopting AI requires much more than connecting an LLM to an application. Enterprise teams must address questions around architecture, governance, security, developer experience, platform capabilities, and operational resilience.

This course provides a practical roadmap for designing and operating AI-enabled systems in modern organizations. You’ll explore topics such as Domain-Driven Design for AI applications, on-premise AI strategies, AI adoption and organizational change, enterprise AI platforms, and the evolving role of product management in AI-driven organizations. The focus is always on creating scalable, governable, and business-ready solutions that deliver measurable value.

Take Your Skills to The Next Level

Session | AI Literacy for Developers: Thinking Clearly While AI Writes the Code | Russell Miles

As AI increasingly takes over code generation, the role of the developer is evolving from writing every line of code to shaping the systems, constraints, and context that guide intelligent tools. This session explores what AI literacy means for modern software engineers and why understanding architecture, intent, feedback loops, and critical evaluation is becoming more important than syntax itself.

Through practical examples and real-world scenarios, you’ll learn how to work effectively with AI coding assistants, identify the risks of blindly trusting generated code, and design systems that remain maintainable, scalable, and understandable. The session provides a forward-looking perspective on how developers can thrive in an era where AI writes more code—but humans remain responsible for making the right decisions.

Article | Vibe Coding: Vibe Mastery or Myth? | Garima Bajpai

Is Vibe Coding a real competitive advantage or just the latest AI buzzword? This session explores how developers and organizations can move beyond hype and understand the conditions that enable creativity, productivity, and effective collaboration with AI.

Learn how culture, workflows, tools, and team dynamics influence successful AI adoption, and discover practical strategies for turning experimental AI-assisted development into sustainable business value.

Article | Turn Vibe Code Into Enterprise Wins in Early Adoption Stages | Garima Bajpai

Early AI experiments often create excitement—but how do you turn promising prototypes into real business outcomes? This session explores how organizations can transform AI-driven experimentation, vibe coding, and rapid prototyping into scalable, enterprise-ready solutions.

Learn practical approaches for balancing innovation and governance, accelerating adoption, and creating the conditions that allow early AI initiatives to deliver measurable value across the organization.

Session | Bootiful Spring AI | Josh Long

Learn how to build modern, enterprise-grade AI applications using Spring Boot 4, Spring AI, and the latest Java features. This session demonstrates how to combine modular architecture, event-driven design, resilient service integration, and AI capabilities into maintainable production systems.

You’ll also explore practical approaches for observability, security, Passkeys, multi-factor authentication, and Spring Modulith, helping you create scalable, secure, and future-proof applications.

Article | Model Context Protocol Under the Microscope | David Caspar & Ole Wendland

As AI systems become increasingly integrated into enterprise architectures, understanding the Model Context Protocol (MCP) is becoming essential. This session explores how MCP enables reliable communication between AI models, tools, and enterprise systems by establishing clear context boundaries and interaction patterns.

Learn how well-defined protocols, context management, and integration strategies help create scalable, maintainable, and trustworthy AI-native applications while avoiding unnecessary complexity and coupling.

Article | Mastering the MCP Server with Spring Boot and AI | Patrick Baumgartner

Learn how to build and extend an MCP Server using Spring Boot and modern AI technologies. This session demonstrates how AI-powered capabilities can be integrated into enterprise applications to enable intelligent automation, streamlined workflows, and more effective interactions between models, tools, and systems.

Discover practical implementation patterns, scalability considerations, and best practices for building production-ready MCP solutions in the Java ecosystem.

Session | Java, AI Agents, and the Cloud-Native Shift | Natale Vinto

Discover how modern Java frameworks such as Quarkus and LangChain4j enable the development of scalable, cloud-native AI agent systems. This session explores how to build intelligent applications that combine RAG, MCP, observability, security, and enterprise-grade governance with autonomous agent workflows.

Learn proven patterns for multi-agent orchestration, tool integration, and human-in-the-loop processes, and see how Java can power reliable, production-ready AI systems far beyond simple model inference.

Article | Composing an Agentic Internal Developer Platform | Russell Miles

What happens when an Internal Developer Platform (IDP) evolves from a passive tool portal into an intelligent, proactive engineering assistant? This session explores how agentic platform architectures can automate workflows, orchestrate developer tasks, and actively support teams throughout the software delivery lifecycle.

Learn how to design a platform from modular AI-driven agents that handle responsibilities such as environment provisioning, deployment automation, operational workflows, and developer self-service. Discover how agentic platforms integrate with existing tooling, reduce cognitive load, improve developer experience, and create the foundation for a more scalable and productive engineering organization.

Article | Building a GraphRAG Application with Spring AI Advisors | Jennifer Reif

Learn how to combine GraphRAG, Spring AI, and knowledge graphs to build AI applications that deliver more accurate, context-aware responses. This session demonstrates how Spring AI Advisors can orchestrate retrieval and generation workflows while leveraging graph relationships to uncover connections traditional vector search often misses.

Using practical examples, you’ll explore how to integrate graph databases, implement retrieval-augmented generation (RAG) with interconnected data, and build intelligent applications that can reason across complex information networks. The session provides actionable guidance for developers looking to move beyond basic RAG architectures and create more powerful, enterprise-ready AI systems with the Spring ecosystem.

Session | Building Agentic AI with Small Language Models | John Davies

Discover how to build agentic AI applications using local language models, with a focus on privacy, low latency, and enterprise-ready deployment. This session explores how modern small LLMs can power intelligent workflows directly on local machines, browsers, and mobile devices—reducing cloud dependencies while maintaining impressive capabilities.

You’ll learn how to evaluate and run local models, manage context windows, optimize tokenization, and implement tool-calling and agentic workflows in real-world applications. Through practical demonstrations and architectural insights, the session also covers multimodal AI, structured outputs, MCP integration, and the use of Java-based frameworks such as Spring and inBabel for building scalable, privacy-conscious AI systems.

Session | The Ultimate Guide to Browser-Based AI | Maxim Salnikov

Discover how modern web technologies are making browser-native AI a reality. This session explores how developers can run LLMs and AI models directly in the browser, enabling privacy-first, offline-capable, and highly responsive user experiences without relying on backend inference services.

You’ll learn how emerging standards such as WebNN, together with technologies like ONNX Runtime Web, Transformers.js, and modern browser hardware acceleration through CPUs, GPUs, and NPUs, are transforming AI development on the web. Through practical examples and demos, the session demonstrates how to build intelligent web applications that benefit from local inference, reduced latency, lower infrastructure costs, and greater user data sovereignty.

Article | Threat Modeling in 45 Minutes | Christian Schneider

Learn how to integrate threat modeling into everyday development without slowing down delivery. This session presents a practical, lightweight approach for identifying and prioritizing security risks in as little as 45 minutes, making security a natural part of modern engineering workflows.

You’ll explore proven techniques such as STRIDE, rapid architecture analysis, risk prioritization, and collaborative security workshops. The session demonstrates how development, architecture, and security teams can work together to uncover vulnerabilities early, create actionable mitigation plans, and improve the overall security posture of applications without introducing excessive process overhead.

Expert Knowledge for...

Software Architects, who want to design scalable and governable AI-native enterprise systems
Engineering Leaders, who need to integrate AI capabilities into platforms, teams, and delivery processes
Platform Engineers, who want to build reliable foundations for AI-powered development workflows
Product Managers, who need to understand how AI changes products, organizations, and decision-making
Developers and Technical Leads, who want practical guidance for building production-ready AI applications

Complete the Course and Learn How to...

design AI-native architectures for modern enterprise environments
integrate RAG, MCP, agentic workflows, and intelligent automation into enterprise systems
apply Domain-Driven Design principles to AI-enabled applications
evaluate when on-premise AI is the right choice for privacy, compliance, and control
build scalable platforms that support AI development and operations