Optimizing Complex Workflows with Event-Driven Multi-Agentic Approach
summary
Claims an architecture that wires event streaming + RAG pipeline to multiple specialised agents and demonstrates concrete integrations: Kafka-style topics for async routing, LangChain4J on Quarkus as the Java control plane, and the mCP protocol plus examples like Microsoft Autogen, Crew AI and LGraph. Covers practical tradeoffs—observability and debugging costs, typical RAG chunking and orchestration steps, and an energy note (LLMs can be ~10× heavier than search)—so useful if the goal is an implementable, event-driven multi-agent pipeline.
AI-written summary · about
chapters (10)
- 0:00Introduction and background
- 3:48Generative AI overview
- 11:00Event-driven architecture
- 16:49Understanding RAG
- 19:36Agents and multi-agent systems
- 25:13Building blocks and standards
- 28:26Event-driven agent workflows
- 32:45Agentic design patterns
- 36:55Frameworks and best practices
- 42:43Challenges, resources, and Q&A
related talks
59mOptimizing Complex Workflows with Event - Driven - Multi Agentic Approach
50mHarnessing Event-Driven and Multi-Agent Architectures for Complex Workflows in Gen...
49mAgentic AI Patterns
47mAgentic AI Patterns
50mPractical Agentic RAG with SpringAI in Modern Enterprise Applications
31mBuilding and Orchestrating Real Production-ready Agentic AI Systems
31mAgentic AI architecture patterns
20mEnhancing RAG with Multi-Agent Integration