Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Agent Communication Protocol

  • up to 2 hours
  • Intermediate

Introducing ACP: Agent Communication Protocol, a short course built in partnership with IBM Research’s BeeAI. Learn to connect agents through ACP, a protocol that standardizes communication between agents, enabling collaboration across different frameworks. By the end of the course, you'll be able to create ACP-compliant agents that can communicate and collaborate effectively.

  • Agent Communication Protocol
  • Multi-agent systems
  • Client-server architecture
  • Workflow management
  • Agent integration

Overview

In this course, you will learn to build ACP-compliant agents by wrapping them in an ACP server, launching the server to activate the agents, and making them discoverable by ACP clients. You will explore how to chain ACP-compliant agents in linear and hierarchical workflows and use a router agent to delegate tasks. The course will guide you through importing ACP-compliant agents into a registry for easy discovery and sharing across teams. By the end, you'll be equipped to create agents that can communicate regardless of their frameworks, enhancing collaboration and integration within multi-agent systems.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

AI Builders

AI builders who want to easily reuse and connect multiple agents built with different frameworks in a single system.

Tech Enthusiasts

Anyone curious to learn about the Agent Communication Protocol and its applications in multi-agent systems.

Developers

Developers interested in integrating and managing agents across different frameworks using a standardized protocol.

This course offers key benefits such as learning to build ACP-compliant agents and integrating them into multi-agent systems. It covers essential topics like agent communication, workflow management, and client-server architecture. Ideal for AI builders and developers, this course will enhance your ability to manage and integrate agents, advancing your career in AI development.

Pre-Requisites

1 / 3

  • Some experience with Python is recommended.

  • Basic understanding of multi-agent systems.

  • Familiarity with client-server architecture.

What will you learn?

Introduction
Introduction to the course and overview of the Agent Communication Protocol.
Why Agent Communication Protocol
Understanding the need for a standardized communication protocol between agents.
ACP Core Principles
Exploring the core principles of the Agent Communication Protocol.
Building a RAG Agent with CrewAI
Learn to build a RAG agent using CrewAI with practical code examples.
Wrapping the RAG Agent into an ACP Server
Steps to wrap a RAG agent into an ACP server with code examples.
Calling an ACP Agent using the Client
How to call an ACP agent using the client with practical examples.
Wrapping a Smolagents Agent into an ACP Server
Learn to wrap a Smolagents agent into an ACP server with code examples.
Sequentially Chaining the Agent Calls
Techniques for sequentially chaining agent calls with code examples.
Hierarchically Chaining the Agent Calls using a Router Agent
Building hierarchical workflows using a router agent to delegate tasks.
Adding MCP to the Hospital Server
Integrating MCP with the hospital server using code examples.
Managing ACP Compliant Agents
Strategies for managing ACP-compliant agents effectively.
Conclusion
Wrapping up the course with key takeaways and next steps.
Quiz
A short quiz to test your understanding of the course material.
Appendix – Resources, Tips, and Download
Additional resources, tips, and downloads to support your learning.

Upcoming cohorts

  • Dates

    start now

Free