2025-11-08 –, Talk Track 3
Living on Washington State’s peninsula offers endless beauty, nature, and commuting challenges. In this talk, I’ll share how I built an agentic AI system that creates and compares optimal routes to the mainland, factoring in ferry schedules, costs, driving distances, and live traffic. Originally a testbed for the Model Context Protocol (MCP) framework, this project now manages my travel schedule, generates expense estimates, and sends timely notifications for events. I’ll give a comprehensive overview of MCP, show how to quickly turn ideas into working agentic AI, and discuss practical integration with real-world APIs. Attendees will leave with actionable insights and a roadmap for building their own agentic AI solutions.
Objective:
This talk aims to demonstrate how agentic AI, powered by the Model Context Protocol (MCP) framework, can solve real-world commute planning challenges for Washington State residents—integrating ferry schedules, costs, driving distances, and live traffic into actionable travel solutions.
Outline:
- The peninsula commute problem
- Why agentic AI and MCP?
- System architecture: APIs, data, and agentic workflows
- Demo: Planning a trip from Kitsap to Bellevue
- Expense estimation and notifications
- Lessons learned: Integration, edge cases, and scaling
- Q&A and roadmap for your own agentic AI
Central Thesis:
Agentic AI, when combined with the MCP framework and real-world data sources, enables rapid development of practical, context-aware solutions for complex travel and event management problems.
Key Takeaways:
- How to use MCP to orchestrate agentic workflows
- Strategies for integrating external APIs (WSDOT, Google Maps, Elasticsearch)
- Approaches for handling real-world constraints (schedules, costs, traffic)
- Tips for rapid prototyping and deployment
- Common pitfalls and how to avoid them
Background Knowledge Expected:
- Basic understanding of Python
- Familiarity with APIs and web services
- General interest in AI, automation, or commute planning
- No prior experience with MCP required (intro provided)
Previous knowledge expected
Justin started his Software Engineering career as a Web Development Boot Camp Instructor where he developed a passion for exciting others with new concepts and empowering individuals with the tools needed to excel in their own right. As an Advocate at Redis, Justin created numerous videos breaking down Data Structures into easy-to-understand, relatable examples with real-world use cases. Now at Elastic, he has expanded into the realm of enhanced search, monitoring, and observability capabilities.
In his spare time, Justin enjoys hiking around the Pacific Northwest, building hobby electronics, and collecting vintage music synthesizers. His love of hardware and software has led him into a deep exploration of IoT for practical applications as well as performance art!