Building Agentic Applications with Spring AI
summary
Claims that Java and Spring can run production agentic apps at enterprise scale using Spring AI, connecting to AWS Bedrock and exposing Java services via Model Context Protocol (MCP). Demonstrates a travel-booking agent built in days that uses chat memory, RAG with a vector DB, function/tool calling and MCP-wrapped Java beans; initial prototype works end-to-end in demos but real reliability requires adding validation, human-in-loop checks and service shims to close the final 20–30% gap.
AI-written summary · about
chapters (11)
- 0:00Intro
- 1:58What are AI agents?
- 3:06Example: Travel assistant service
- 5:07AI agents simplified
- 5:33Why Java & Spring AI are important for agentic?
- 8:03how can we create agents with Spring AI?
- 9:19How it works?
- 13:06But that's not the whole story
- 16:31The 12 Factor Agent
- 18:00Demo
- 23:11Outro
related talks
49mSpring AI: Seamlessly Integrating AI into Your Enterprise Java Applications
54mFrom Single-Shot LLMs to Intelligent Agents: Building Scalable AI Systems with Spring AI and MCP
01h 52mDiving into Spring AI: Building Production-Ready Agentic Applications
54mSpring AI Is All You Need
26mJava’s GenAI Era: Getting Spring AI and Neo4j Applications to Production
51mIntelligent Applications with Spring AI
52mIntelligent Beans with Spring AI
52mBeyond local tools: Deep dive into MCP with Spring AI