Chris Heilmann, Daniel Cranney & Tiffany Souterre
Build a Multi-Agent Role-Playing Game Master with Strands Agents
#1about 2 minutes
Understanding the fundamentals of AI agents
AI agents are large language models (LLMs) enhanced with the ability to perform actions using external tools.
#2about 2 minutes
Standardizing agent-tool communication with MCP
The Model Context Protocol (MCP) provides a standardized way for AI agents to connect with and use various tools, similar to REST APIs.
#3about 1 minute
Enabling agent collaboration with the A2A protocol
The Agent-to-Agent (A2A) protocol standardizes communication and collaboration between different AI agents.
#4about 2 minutes
Getting started with the Strands SDK for agents
The Strands SDK from AWS simplifies building multi-agent workflows by handling MCP and A2A protocols with just a few lines of code.
#5about 4 minutes
Creating a basic agent and using local models
Learn how to instantiate a simple agent and configure it to use different LLM providers, including local models via Ollama.
#6about 9 minutes
Adding capabilities with built-in and custom tools
Give agents new abilities by importing pre-built tools or creating your own custom functions using the `@tool` decorator.
#7about 5 minutes
Serving tools remotely with an MCP server
Decouple tools from your agent by running them on a dedicated MCP server, making them accessible to any connected agent.
#8about 12 minutes
Building a multi-agent system with the A2A protocol
Create a collaborative system by running specialized agents on A2A servers and connecting them to a primary orchestrator agent.
#9about 3 minutes
Showcasing the complete multi-agent game master
A full demonstration shows a game master agent orchestrating a character agent, a rules agent, and a dice-rolling tool via a UI.
#10about 1 minute
Conclusion and resources for getting started
Find links to the Strands SDK documentation, code samples, and a discount code for AWS re:Invent.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
1:21:54 MIN
Demonstrating a complete multi-agent AI game master
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds
45:04 MIN
Understanding AI agents, MCP, and the Strands SDK
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds
02:56 MIN
Why Dungeons & Dragons is a great use case for AI agents
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds
18:03 MIN
GenAI applications and emerging professional roles
Enter the Brave New World of GenAI with Vector Search
22:52 MIN
The future of AI protocols and agent ecosystems
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
20:54 MIN
Live code demo of various AI application patterns
Building AI Applications with LangChain and Node.js
1:10:12 MIN
Creating a multi-agent system using the A2A protocol
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds
08:28 MIN
A practical demo of an agent using multiple tools
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
Featured Partners
Related Videos
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds
Chris Heilmann, Daniel Cranney & Tiffany Souterre
AI: Superhero or Supervillain? How and Why with Scott Hanselman
Scott Hanselman
On a Secret Mission: Developing AI Agents
Jörg Neumann
Beyond Chatbots: How to build Agentic AI systems
Philipp Schmid
Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP
Viktoria Semaan
Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact
Oliver Will
Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure
Ricardo
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
Brad Axen
From learning to earning
Jobs that call for the skills explored in this talk.

Senior AI Software Developer & Mentor
Dynatrace
Linz, Austria
Senior
Java
TypeScript
AI Frameworks
Agile Methodologies

Lead Fullstack Engineer AI
Hubert Burda Media
München, Germany
€80-95K
Intermediate
React
Python
Vue.js
Langchain
+1




Machine Learning Engineer - AI-Features, Agenten & Multi Agenten Workflows
dmrz
API
.NET
DevOps
Python
Microservices
+2


