Supercharge Agentic AI Apps: A DevEx Driven Approach to Cloud-Native Scaffolding
summary
Shows a concrete Java stack: Quarkus + LangChain4j + MCP integration that turns a few annotations and config into a working agentic app, with one annotation to register AI service and MCP subprocesses launched automatically plus auto-started testcontainers and OpenTelemetry. Demonstrates a restaurant-finder demo that chains web search, maps, memory and calendar actions and can report which tool ran each step. Notes ecosystem scale—200+ MCP servers and Hugging Face hosting ~1.66M models—and a Backstage template that scaffolds cloud deployment and CI.
AI-written summary · about
chapters (9)
- 0:00Introduction to agentic AI
- 7:28What is agentic AI
- 12:07Agentic vs traditional apps
- 17:50Java frameworks for agentic AI
- 22:50Demo setup with Quarkus
- 31:28Live demo of agentic workflow
- 40:49Internal developer portals
- 47:50Demo architecture and roadmap
- 49:39Key takeaways and conclusion
related talks
01h 06mSupercharge #AgenticAI Projects A DevEx Driven Approach to #CloudNative Scaffolding
06m⚡ Lightning Talk: Supercharge Agentic AI Apps: A DevEx-Driven Approach To Cloud Native Scaffolding
47mCreating AI-infused Apps, the Easy Way 🤙
31mBuilding and Orchestrating Real Production-ready Agentic AI Systems
52mBeyond local tools: Deep dive into MCP with Spring AI
33mAI-infused command-line applications
28mBuilding Agentic AI applications on AWS
01h 01mCreate #AI Infused #Java Apps with #LangChain4j