WeAreDevelopers LIVE Sep 30, 2025

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

Chris Heilmann , Daniel Cranney , Tiffany Souterre

Standardizing agent-to-tool communication eliminates redundant code. Learn how to architect a scalable, multi-agent RPG Game Master using Model Context Protocol and the open-source Strands SDK.

Pause
Mute Enter Fullscreen
#1 about 3 min

Defining autonomous agents and tool integrations

Adding external tools to conversational AI converts static text generators into actionable software entities.

#2 about 3 min

Standardizing agent communication with MCP and A2A

The Model Context Protocol and Agent-to-Agent protocol standardize connections between models, tools, and collaborating agents.

#3 about 4 min

Initializing a simple agent using the Strands SDK

Installing the Strands framework and instantiating an agent enables rapid connection to cloud-based language models.

#4 about 3 min

Executing query resolution with local Ollama models

Connecting the framework to a locally hosted model provides offline capabilities for localized testing.

#5 about 3 min

Importing built-in functions to overcome context limitations

Applying pre-built community tools to an agent provides real-time information access previously missing from training data.

#6 about 3 min

Writing and executing files dynamically with AI tools

Adding file manipulation capabilities lets models autonomously author, read, and execute external scripts directly.

#7 about 5 min

Creating custom agent tools using Python decorators

Wrapping a standalone Python function with a configuration decorator exposes internal application logic to model orchestration.

#8 about 6 min

Deploying custom functions onto an MCP server

Migrating native tools to a dedicated server endpoint enables standardized function consumption across disparate models.

#9 about 6 min

Building specialized sub-agents with the A2A server

Configuring an independent agent with focused prompts allows the system to delegate highly specific computational workloads.

#10 about 6 min

Connecting multi-agent systems for workflow orchestration

Passing endpoint parameters back to a master orchestrator empowers language models to collaboratively request tasks and exchange data.

#11 about 5 min

Testing the completed multi-agent database workflow

Deploying the fully assembled architecture showcases dynamic interactions spanning interface inputs, local APIs, and specialized knowledge bases.

Matching moments

3:03 min

Using large language models as tabletop game masters

Chris Heilmann +2 · LIVE

3:25 min

Understanding foundational concepts of LLMs, agents, and MCPs

Perf + AI

1:42 min

Standardizing autonomous agent logic with model context protocol

Timo Salm Timo Salm · WWC 2025

5:37 min

Architectural patterns for composing dynamic AI agents

Philipp Schmid Philipp Schmid · WWC 2025

2:02 min

Moving from playing with artificial intelligence to business implementation

Lee Stott · Coffee With Developers

1:32 min

Building autonomous functions with conversational agent frameworks

Modood Alvi · WWC 2025

Upcoming sessions on this topic

Open session

World Congress 2026 North America

MicroAgents: The Microservices of the Agentic Era

Ashish Shubham

Runs the show bussiness at ThoughtSpot

Ashish Shubham
Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anjana Umapathy, Apoorva Jaiswal, Anagha Rumade

Anjana Umapathy
Apoorva Jaiswal
Anagha Rumade
Open session

World Congress 2026 North America

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

Making (and Breaking) Agents by Adding 1,000 MCP Tools

Guillaume Lebedel

Stackone, CTO & Co-Founder

Guillaume Lebedel
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

AI-Powered Incident Triage: How We Built GenAI Agents with MCPs to Automate On-Call Workflows

Prakshal Doshi

Site Reliability Engineer

Prakshal Doshi