Building AI Agents with Spring AI and Tanzu Platform
summary
Claims that the JVM plus Spring AI and Tanzu Platform let teams move from experiments to production with concrete results: a benchmark shows Java <1ms P95 and ~1,624 RPS versus much higher latency in Python, a deployed demo uses a Pooch Palace assistant, OAuth server, scheduler, OpenAI/PGVector and a model marketplace with a 120B GPT-OSS plan, and a build-failure analyzer processes 27,000 daily builds with 2,500 failures. Platform features include model provisioning, per-model API keys and AOT 40% startup improvements via CF push.
AI-written summary · about
chapters (8)
- 0:00Introduction and welcome
- 3:59Spring AI and AI agents
- 13:29Portability and model switching
- 23:10MCP security and OAuth
- 30:07Deploying to Tanzu Platform
- 36:24Build failure analysis case study
- 43:05AOT caching and startup speed
- 53:17Summary and closing
related talks
24mBuilding Agentic Applications with Spring AI
51mSupercharging Spring AI: Scalable AI Agents with Koog + Spring AI + Spring Boot
52mIntelligent Beans with Spring AI
01h 00mSpring AI
21mSpring Unlocks the Power of AI Platform - End-to-End
54mSpring AI Is All You Need
44mBootiful Spring Boot
42mBootiful Spring AI