Full-Stack AI Engineering - Auckland

RSVP: luma.com/mate

Hi all, another great session about AI native development. Ezequiel Lanza, an AI Software Engineer and Evangelist at Intel will join us from Toronto to present, answer your questions and have a chat with folks who are in the frontier of AI development. Join us!

From Image to Itinerary: Multimodal Agentic Travel Planning with MCP, A2A, and BeeAI

​Abstract:
​Planning a trip from visual input is a deceptively complex problem for AI. In this session, we present a multimodal-first, local-first agentic architecture where a user uploads an image (e.g. “where is this place?”), and the system generates a travel plan using Model Context Protocol (MCP) and A2A (Agent-to-Agent), running fully locally without cloud dependencies.

​Models are executed using OpenVINO and OpenVINO Model Server, enabling optimized inference across CPUs and GPUs with minimal configuration. They are automatically optimized and exposed through simple local APIs, allowing developers to interact with them as if they were cloud services—without managing infrastructure.

​The system follows a router and specialist agent pattern, where dedicated agents handle image understanding, hotel search, and flight search via MCP servers. A multimodal model extracts meaning from the image, and the router decomposes and delegates tasks across agents through A2A.

​We focus on practical architecture, configuration, and lessons learned for building MCP-centric, multimodal systems that are extensible, reproducible, and production-ready—while remaining fully local and efficient.

About the speaker:

Ezequiel Lanza is an AI Software Engineer and Evangelist with a passion for making artificial intelligence practical and accessible to developers.

As a regular speaker at leading AI and open-source conferences, he creates impactful use cases, tutorials, and guides that help teams adopt and deploy open-source AI tools effectively.  With a strong engineering background and over two decades of experience supporting developers and customers in the software industry, Ezequiel brings a unique blend of technical expertise and real-world perspective. He holds a master's in data science at Universidad Austral in Argentina.

Ezequiel was elected as a Board Member and TAC Chair of the Linux Foundation AI & Data, where he helped shape the future of open-source AI and foster collaboration across the global ecosystem.

We’re excited to bring Agentic Build Day to New Zealand this October 21–22, 2026 in Auckland.

Agentic Build Day is an independent, community-driven conference for software engineers, architects, builders, and curious minds exploring what it really means to work with AI systems in practice. From agents and emerging standards like MCP, SKILLS, to orchestration, evaluation, governance, observability & tracing, security, memory & context management and infrastructure - this is about the messy, real-world challenges of moving Cognitive Architectures out of the lab and into hardened, reliable production systems.

Whether you're experimenting with your first agent or scaling complex AI systems, this is a space to learn, share, and help shape the future of the local industry - together.

Note: Make sure to register to secure your seat! There is limited space available.

Agentic Build Day is a paid event with community-priced tickets. Join us and support!

Call for papers OPEN!

If you're building agentic systems, shipping them into production, or pushing the boundaries of what autonomous AI can do, we want to hear about it.

Share what you're learning with the community and let’s build the future of agentic systems together.

Submissions are open now → https://www.agenticbuild.day/