Skip to content

WORKSHOP

Small Agents. Big Mesh. Build Production-Grade Agentic AI Systems with Solace Agent Mesh (Hands-On)

Date: 12th March 2026 | Time: 3:30 PM to 6:00 PM

Venue: Workshop Room 2, NIMHANS Convention Centre, Bangalore

FEES:
• Rs.299 for Leaders Pass holders
• Rs.2,009 for Professionals Pass holders
• Rs.2,249 for Knowledge Pass holders
• Rs.2,699 for Community Pass holders
• Rs.2,999 for Expo Pass holders
(Limited seats available)

Giri Venkatesan

Principal Developer Advocate, Solace

Suresh Kumar Palaka

Director, TechCOE

From Agentic AI Demos to Production Systems
Introduction: 20 Minutes

  1. Why Agentic AI Demos Don’t Survive Reality
  2. Agentic AI Is a Distributed Systems Problem
  • Single agents vs agent ecosystems
  • Why centralized orchestration breaks at scale
  • Agents as autonomous, long-running services
  • Why event-driven coordination fits enterprise conditions
  1. Agent Mesh as a Practical Pattern
    What an agent mesh enables:
  • loose coupling
  • asynchronous coordination
  • dynamic capability discovery


How Solace Agent Mesh applies this pattern:

  • agents connected via real-time events
  • A2A and MCP-based integration
  • evolve workflows without rewiring pipelines
  1. What “Production-Grade” Actually Means
  • Handling retries and partial failures
  • Managing state and context over time
  • Observability and auditability via events
  • Scaling agents independently


Hands-On Focus (Remaining time – 100 Minutes)

In the accompanying hands-on workshop, participants will build a simple multi-agent system using Solace Agent Mesh, connecting agents through events instead of direct calls. The lab focuses on adding, evolving, and observing agents under realistic conditions, including failures and workflow changes – to demonstrate how event-driven agent architectures scale
beyond demos into production-ready systems

Benefits/Takeaways of this workshop for the attendees (What will attendees do after attending the workshop which they were not able to do before attending this)

  1. Enterprise agentic AI is a distributed systems problem, not a prompt engineering problem
  2. Centralized, synchronous orchestration does not scale for real-world agent workflows
  3. Event-driven coordination enables loose coupling, resilience, and independent scaling of agents
  4. Production-grade agentic systems must handle retries, back-pressure, partial failures, and evolving workflows
  5. Treating agents like autonomous services improves reliability, ownership, and system evolution
  6. Architecture, not models — ultimately determines whether enterprise GenAI systems earn trust and deliver value

About Speakers

Giri Venkatesan is an Architect & Developer Advocate with extensive experience in integration and master data management. Experienced in EAI & B2B Integration space and has been a part of the integration evolution culminating in modern EDA, microservices, Spring, and other low-code/no-code frameworks. He has a keen interest in building and promoting creative solutions and is a huge fan of open-source standards and applications.

Suresh Palaka is a technology leader with over 20 years of experience in enterprise architecture, event-driven systems, and large-scale digital transformation initiatives. As Director of Technology (CoE), he works closely with global enterprises and system integrators to design scalable, secure, and future-ready integration solutions.