Chris Heilmann, Daniel Cranney & Tiffany Souterre

Build a Multi-Agent Role-Playing Game Master with Strands Agents

Go beyond simple chatbots. Learn to build a team of collaborating AI agents that can orchestrate and run a complete role-playing game.

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

Demonstrating a complete multi-agent AI game master
07:40 MIN

Demonstrating a complete multi-agent AI game master

WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds

Understanding AI agents, MCP, and the Strands SDK
06:07 MIN

Understanding AI agents, MCP, and the Strands SDK

WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds

Why Dungeons & Dragons is a great use case for AI agents
08:31 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

Creating a multi-agent system using the A2A protocol
11:42 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

Building agents and simplifying complex tasks
04:25 MIN

Building agents and simplifying complex tasks

30 powerful AWS hacks in just 30 minutes: Boost your developer productivity

Building a simple agent and connecting to local models
05:11 MIN

Building a simple agent and connecting to local models

WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds

Building enterprise-grade AI agentic solutions
02:43 MIN

Building enterprise-grade AI agentic solutions

AI for Enterprise Developers - Dr. Damir Dobric

Understanding the core components of an AI agent
03:01 MIN

Understanding the core components of an AI agent

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure

Featured Partners

Related Videos

See all videos
WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds1:32:50

WeAreDevelopers LIVE - Build a multi AI agents game master with Strands & our weekly web finds

Chris Heilmann, Daniel Cranney & Tiffany Souterre

Machine Learning for Software Developers (and Knitters)49:45

Machine Learning for Software Developers (and Knitters)

Kris Howard

AI: Superhero or Supervillain? How and Why with Scott Hanselman25:17

AI: Superhero or Supervillain? How and Why with Scott Hanselman

Scott Hanselman

Beyond Chatbots: How to build Agentic AI systems24:22

Beyond Chatbots: How to build Agentic AI systems

Philipp Schmid

On a Secret Mission: Developing AI Agents29:03

On a Secret Mission: Developing AI Agents

Jörg Neumann

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP25:32

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Viktoria Semaan

Azure AI Foundry for Developers: Open Tools, Scalable Agents, Real Impact23:33

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 Azure26:35

Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure

Ricardo

Related Articles

View all articles
DC
Daniel Cranney
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity
Inside last week’s Dev Digest 210 . 🪦 Is MCP already dead? 🐍 Secure snake on the CLI 🏗️ The architecture behind open source LLMs ⚖️ AI companies and governments at odds 🦫 Is Go the best language for AI agents? 🕵️ “Security research” bot hacks Micros...
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity
DC
Daniel Cranney
Dev Digest 211: Securing Agents, Top AI Apps and Lost Readers…
Inside last week’s Dev Digest 211 . 🏗️ Can the infrastructure keep up with AI growth? 📱 Top 100 GenAI consumer apps 🪱 Wikipedia hit by worm and AI slop 🔍 The results of Codex Security scanning 1.2M commits 🧹 Bye bye innerHTML, welcome setHTML() 🔄 Cl...
Dev Digest 211: Securing Agents, Top AI Apps and Lost Readers…
CH
Chris Heilmann
WebMCP: Empowering Agents as First-Class Citizens of the Web
WebMCP is an exciting W3C proposal that just landed in Chrome Canary to try out . The idea is that you can use some HTML attributes on a form or register JavaScript tool methods to give agents direct access to content. This gives us as content prov...
WebMCP: Empowering Agents as First-Class Citizens of the Web

From learning to earning

Jobs that call for the skills explored in this talk.