Design AI-Powered Experiences with MCP, Agent-to-Agent Orchestration, and Skills

Closed captions in English will be available soon.

Share this page

Speakers

  • Trent Davies

    Trent Davies

    Senior Principal Architect, Adobe

Featured Products

Session Resources

About the Session

Learn how to design AI-powered experiences using the emerging agent integration stack of Model Context Protocol (MCP), agent-to-agent (A2A) orchestration, and composable Skills. This session builds a practical mental model for how these layers fit together, when to use each one, and how to mix them safely in production. See how leading tools like Claude Code, Cowork, Codex, and Antigravity plug into this stack, explore common patterns and anti-patterns, and walk away with a decision framework that helps your teams ship reliable, extensible AI features faster.
Key takeaways

  • Understand the core roles of MCP, A2A orchestration, and Skills in the AI integration stack
  • Identify proven design patterns and anti-patterns for connecting agents to tools and to each other
  • Apply a simple decision framework to choose the right integration approach for your next AI use case

Technical Level: Beginner to Intermediate

Track: Developers , Orchestrating Experiences with AI Agents

Content Category: Thought Leadership

Audience : Developer, IT , Martech Professional, AI Strategy/Technology

This content is copyrighted by Adobe Inc. Any recording and posting of this content is strictly prohibited.


By accessing resources linked on this page ("Session Resources"), you agree that 1. Resources are Sample Files per our Terms of Use and 2. you will use Session Resources solely as directed by the applicable speaker.