Your cart is empty.
Keep shoppingAgentic AI RCA System : Spring Boot MCP with Enterprise POC
Hot & New
New
137 students
Agentic AI RCA System : Spring Boot MCP with Enterprise POC
Build an agentic AI incident investigator with Spring Boot, MCP tools, Splunk logs, Jira and RCA.
Created byCode Decode
Last updated 8/2026
English
English [Auto],
What you'll learn
- Build an Agentic AI production incident investigator using Spring Boot, Spring AI and MCP.
- Understand how MCP tools allow AI Agents to safely access logs, incidents and backend systems.
- Implement structured logging, correlation IDs and Splunk-based investigation for microservices.
- Create incident scenarios such as payment success but order confirmation failure.
- Integrate Splunk alerts with Jira using ngrok and a Spring Boot helper service.
- Generate evidence-backed RCA using AI, logs, business state, service health and incident evidence.
- Understand the difference between chatbot, workflow automation, generative AI and Agentic AI.
- Apply this architecture to real Java backend projects for production debugging and support.
Explore related topics
Course content
6 sections • 63 lectures • 4h 44m total length
Requirements
- Basic Java and Spring Boot knowledge is recommended.
- Basic understanding of REST APIs, controllers, services and database operations.
- Familiarity with microservices concepts will help, but the project flow is explained step by step.
- A local development setup with Java, Maven, Node.js, Angular CLI and MariaDB.
- Basic awareness of logs, production support or debugging is helpful but not mandatory.
- Optional: Splunk, Jira and ngrok accounts for running the complete alert-to-ticketing flow.
Description
This course teaches you how to build a production-style Agentic AI project using Spring Boot, Spring AI, MCP, Splunk, Jira, SQL and Angular.
Instead of creating another simple chatbot or CRUD application, you will build an AI-powered production incident investigator for Java backend systems. The project is based on a realistic microservice problem: payment is successful, but the order is not confirmed. This kind of issue requires backend teams to check logs, correlation IDs, business state, service health, incident evidence and RCA.
You will start with an Order and Payment service playground, then add structured logging, correlation ID propagation, Splunk log collection, incident scenario creation, Jira ticketing through a helper service, and an AI Investigation Console.
The core of the course is the Agentic AI flow. You will learn how an AI Agent receives an incident goal, uses MCP tools, collects evidence, checks logs and service health, compares facts, rejects wrong causes and generates evidence-backed RCA.
You will also understand why MCP is important for enterprise AI systems. Instead of giving AI direct access to databases, Splunk or production systems, MCP provides safe and controlled tools.
By the end of this course, you will understand how to design and explain a real backend AI architecture using Spring Boot, Spring AI, MCP, observability, incident management and human-approved remediation.
This course includes demonstrations of AI systems and AI-assisted development workflows. All explanations, architecture decisions and implementation walkthroughs are reviewed and guided by the instructor.
Who this course is for:
- Java backend developers who want to move beyond CRUD APIs and build AI-powered backend systems.
- Spring Boot developers who want to learn Spring AI, MCP and Agentic AI through a practical project.
- Backend engineers who handle production issues, logs, incidents, RCA and support workflows.
- Developers who want to understand how AI Agents can investigate real backend failures safely.
- Microservices developers interested in observability, correlation IDs, Splunk, Jira and incident automation.
- Software engineers who want to build a portfolio-level enterprise AI integration project.