In this hands-on workshop, attendees split into teams - Project Management, Development, QA, and Marketing - to build an AI-enabled development for a fictional airline, AgenticAIrways.
Each team builds an AI agent for its role in the delivery workflow. The PM team defines requirements and passes them to the Dev team, who build features with tool use and domain-specific logic. The Dev team hands off to PM and QA for review and stress-testing with adversarial scenarios and edge cases. Once the system passes muster, it's handed to Marketing to define how the product is communicated to end users.
Agents communicate and coordinate using MCP and Agent-to-Agent (A2A) protocols, mirroring how agentic software will increasingly be embedded in real development workflows.
Whether the airline launches successfully or descends into chaos, every team will walk away with practical experience designing, constraining, and orchestrating multi-agent systems — and a clear understanding of how AI agents can augment each role on a dev team.
163 min
AI on Demand: Serverless AI
Top Content
Featured WorkshopFree
In this workshop, we discuss the merits of serverless architecture and how it can be applied to the AI space. We'll explore options around building serverless RAG applications for a more lambda-esque approach to AI. Next, we'll get hands on and build a sample CRUD app that allows you to store information and query it using an LLM with Workers AI, Vectorize, D1, and Cloudflare Workers.













