At Boston Code Camp 40, I presented an in-person session on building real-time voice AI systems, focusing on the shift from traditional speech pipelines to conversational, audio-native architectures. I demonstrated how legacy approaches introduce latency and disrupt natural interaction, and how modern real-time models enable streaming, low-latency, and interruptible conversations that feel more human. The […]
AI Architecture
Memphis Agent Camp: Building Real-Time Voice AI: From Pipelines to Conversations
At Memphis Agent Camp, I delivered an online session on the evolution of voice AI from rigid, multi-step pipelines to real-time conversational systems. The talk highlighted how audio-first models enable fluid, human-like interactions by reducing latency and supporting continuous, interruptible dialogue. I walked through practical design patterns for building voice-enabled agents that integrate with enterprise […]
Model Context Protocol (MCP): Connecting AI Models to Real-World Systems
At the Nashua Cloud .NET User Group, we explored the Model Context Protocol (MCP) and why it is becoming the execution layer for real AI agents. The session focused on moving beyond prompt-only demos to secure, governed, and reusable tool access for enterprise systems. We covered how MCP introduces a standard client–server model where the […]
Microsoft Agent Framework Dev Day (Hands-on) – Burlington, MA | Workshop Recap
On January 16, 2026, I co-hosted the Microsoft Agent Framework Dev Day (Hands-on) in Burlington, MA, with Bill Wilder and Jason Haley. This full-day workshop was entirely lab-driven and focused on building production-ready AI agents using real architecture patterns. Event details:👉 https://www.meetup.com/bostonazureai/events/312564860/ As part of the Agent Framework Dev Project, attendees implemented end-to-end agent solutions […]
Building Real-Time Voice AI: From Pipelines to Conversations
I recently presented “Building Real-Time Voice AI: From Pipelines to Conversations” at the Nashua Cloud .NET User Group, where we explored how Voice AI is evolving beyond rigid pipelines like Speech → Text → LLM → Text → Speech. Traditional approaches introduce latency, break conversational flow, and make interactions feel unnatural. With the rise of […]