Rey Riel
Senior Developer Advocate @ Solace, helping developers best I can
Ottawa, Canada
Actions
Rey serves as Senior Developer Advocate for Solace. Since 2016 Rey has been advocating for developers, doing what he can to make developers lives easier and more fun, driving awareness and creating code to make developers successful. Being well-versed in a plethora of languages over the last decade has given Rey a vast look at the developer community as a whole. Committed to helping developers of all sorts Rey is also a co-organizer for the ForwardJS Javascript Meetup group, a co-organizer for Random Hacks of Kindness and an organizer for developer focused conferences, including ForwardJS Ottawa.
Area of Expertise
Topics
Stop Wiring Agents to APIs. Build an Agent Mesh Instead
Many agentic AI demos rely on tightly coupled API calls and step-by-step orchestration. This approach works for prototypes, but it breaks down in production environments where failures, latency, retries, and scale are needed. Agents become brittle, workflows are difficult to evolve, and resilience is hard to achieve.
In this session I'll be discussing an alternative architecture: building an Agent Mesh using Event-Driven Architecture. Instead of wiring agents directly to APIs or to each other, agents communicate by publishing and subscribing to real-time events. Each agent focuses on a specific responsibility, reacts to the events it cares about, and emits new events that move the system forward.
Using our open source Solace Agent Mesh as a reference, I'll explain in this beginner-friendly talk how an Agent Mesh enables loose coupling, scalability, resilience, and continuous autonomy for agentic systems. After listening, you'll see why events are a better coordination mechanism than synchronous API chains, and how Event-Driven Architecture provides the backbone that allows agentic AI to move from demos to production-ready systems.
If you want agentic AI to work beyond prototypes, this session explains the architectural shift required.
The Solace Agent Mesh, an open source alternative to making agents talk to each other.
This Show and Tell will walk you through the beauty of the Solace Agent Mesh, where we simplify and streamline the annoyances of A2A and structured workflows in Agentic AI.
Small Agents. Big Mesh. Build Production-Grade Agentic AI Systems with Solace Agent Mesh
Most agentic AI demos work because the demo environment is perfect. Data is static. There is no back-pressure, no retries, and no real ownership boundaries.
Production is different.
In the real world, agents rarely fail because LLMs can't reason. They fail because workflows become brittle. Context gets lost. State becomes stale. Services change. New capabilities must be inserted. Load spikes unpredictably.
This workshop teaches participants how to build event-driven, production-level agentic systems using the Solace Agent Mesh. In this model, agents behave like microservices: autonomous, loosely coupled, independently scalable, and resilient to failure.
Participants will learn how the Solace Agent Mesh coordinates agent ecosystems through real-time events, supports dynamic agent discovery, and integrates agents using A2A and MCP protocols. The result is an architecture that evolves without rewiring pipelines and survives real enterprise conditions.
By the end of the workshop, participants will not just have an agent. They will have a working Agent Mesh: a distributed, orchestrated fabric that allows agents to collaborate across live enterprise environments in a safe, observable, and scalable way.
Getting Started with the Solace Agent Mesh
The Solace Agent Mesh is an open-source framework for building event-driven multi-agent AI systems that solve complex problems through intelligent collaboration. You can use it to create teams of specialized AI agents that work together seamlessly, each bringing unique capabilities while communicating through Solace's proven event-driven architecture.
This workshop will dig a bit deeper into the what why and how of working with the Solace Agent Mesh.
Agents Don't Always Hallucinate, Sometimes They Just Don't Know What Time It Is.
Most agent failures in production are not caused by the model itself. The real issue is data. Your agent might act on information that was true at 6am, even though the situation changed by 9am.
The main difference between demo agents and production agents is data staleness. Batch-refreshed RAG, polling loops, and nightly ETL usually work well, but they fall short when an agent needs to respond to something that happened just twenty minutes ago. In multi-agent systems, a single outdated inference can lead to a wrong answer that other agents rely on, making the problem even bigger before anyone notices.
We'll walk through why event-driven architecture is the right foundation for agents operating on live systems, and cover the engineering decisions that come with it, event-triggered execution, streaming context, agent-to-agent communication patterns, latency budgets, and more.
AgentCon Toronto Sessionize Event
Momentum 2023 Sessionize Event
UtahJS Conf 2023 Sessionize Event
JavaScript & Friends 2023 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top