Vignesh Selvam

Principal Product manager - Amazon MQ

Experienced Product manager with over 12 years of experience in building B2B SaaS products (Data analytics, Risk management, Messaging) and specialized skill sets in analytics, product marketing and pricing. I’ve led multiple teams in developing products across startup, mid-size & enterprise environments.

Talk:
5 Capabilities Your Broker Needs for Agentic Workloads

Every agent framework is quietly reimplementing broker capabilities from scratch. Routing? Reimplemented per-framework. Retries? Each one rolls its own. Discovery, fan-out, backpressure, dead-lettering, durable execution: all reinvented in application code, inside a single process, with predictable results. Message brokers have solved these problems for decades, but today’s brokers weren’t designed for consumers that are stateless, non-deterministic, and expensive to invoke. Both sides need to evolve. This talk identifies the five properties a message broker must take on to serve agentic workloads natively, so agent frameworks can stop pretending to be infrastructure and get back to being applications.

Key Takeaways:

  • Attendees will learn to recognize where agent orchestration frameworks are reimplementing messaging infrastructure,
  • understand the specific demands that agentic workloads place on brokers that today’s designs do not address,
  • and leave with a clear picture of the capabilities their broker must gain to support this new class of consumer.

Target Audience:

  • Messaging engineers, architects, and technical leaders who operate message brokers in production and are starting to see agent-driven workloads arrive on their infrastructure. No prior AI or agent framework experience required.