Abhimanyu Selvan
Event-Driven Architecture: Breaking Conversational Barriers with Distributed AI Agents
#1about 2 minutes
The core challenge of scaling AI agent communication
The speaker introduces the central problem of how to architect communication between thousands of AI agents operating at a global scale.
#2about 2 minutes
Understanding the shift to the agentic era
AI is evolving from reactive systems to an agentic era where software components plan and execute tasks autonomously to achieve high-level goals.
#3about 2 minutes
The core components that define an AI agent
An AI agent is defined by its persona, perception, short and long-term memory, and the tools it can use to perform actions.
#4about 2 minutes
Why event-driven architecture is key for agents
Scaling AI agents presents challenges in state synchronization and observability, making event-driven architecture a necessary paradigm for asynchronous communication.
#5about 2 minutes
Introducing the ride-hailing application demo
A pre-recorded demo showcases an Uber-like application with robo-taxis and users interacting asynchronously, powered by an event-driven backend.
#6about 4 minutes
The system design of the event-driven architecture
The architecture uses Kafka topics for users, taxis, and rides, with an orchestrator agent processing events and a simulator using Mapbox for routing.
#7about 4 minutes
Live demo of the robo-taxi simulation in Berlin
A live demonstration spins up containerized services to simulate users requesting rides and robo-taxis being dispatched in real-time in Berlin.
#8about 2 minutes
The danger of over-engineering with LLMs
A key lesson learned was to avoid unnecessary LLM calls that increase cost and latency, emphasizing the need for observability and pragmatic design.
#9about 3 minutes
Scaling the simulation across multiple cities
The final demo showcases the architecture's scalability by running simultaneous simulations in both Amsterdam and Berlin.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
20:44 MIN
Applying distributed systems principles to AI agents
Composable Intelligence: How Henkel and Microsoft Are Shaping the Agent Ecosystem
05:02 MIN
Moving from monolithic AI to modular agent architectures
Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact
20:42 MIN
Using streaming data to power real-time agent applications
Unlocking Value from Data: The Key to Smarter Business Decisions-
28:16 MIN
The conceptual shift in modern AI development
On a Secret Mission: Developing AI Agents
12:23 MIN
Deconstructing the modern agentic systems stack
The State of GenAI & Machine Learning in 2025
02:04 MIN
Understanding the core components of agentic AI systems
Agentic AI Systems for Critical Workloads
00:06 MIN
The evolution from chatbots to autonomous AI agents
On a Secret Mission: Developing AI Agents
11:13 MIN
Why design patterns are crucial for scalable agents
Beyond Chatbots: How to build Agentic AI systems
Featured Partners
Related Videos
39:11Agents for the Sake of Happiness
Thomas Dohmke
24:22Beyond Chatbots: How to build Agentic AI systems
Philipp Schmid
29:03On a Secret Mission: Developing AI Agents
Jörg Neumann
26:35Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure
Ricardo
35:16How AI Models Get Smarter
Ankit Patel
30:01Agentic AI Systems for Critical Workloads
Mario Fusco
25:14AX is the only Experience that Matters
Ivan Burazin
23:33Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact
Oliver Will
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
AI Engineer Workflows & Agents (e.g. with Langdock, n8n & make)
WaveSix Labs GmbH
Intermediate
GIT
JSON
GraphQL
Microsoft Office
AI Agent Engineer (Machine Learning Engineer)
Zendesk
Berlin, Germany
Remote
FastAPI
Machine Learning
Natural Language Processing