Data Science Dojo – New York

As AI applications grow more complex, single-agent models often struggle with overloaded context, unclear responsibilities, and fragile workflows. Multi-Agent AI solves these challenges by distributing tasks across specialized agents that collaborate, delegate, and execute processes efficiently.
In this session, we’ll explore how to design and implement scalable multi-agent systems using LangChain. You’ll learn when multi-agent architectures are essential, how patterns like subagents, skills, handoffs, and routers work in practice, and how they help manage context, specialization, and task distribution in real-world AI workflows.
A live, hands-on demonstration will show how to define, compose, and orchestrate LangChain agent skills within a framework of collaborating agents. You’ll see how agents collaborate, route tasks intelligently, and scale beyond simple demos into production-ready systems. By the end of the session, you’ll have a clear framework for implementing these systems in your own projects.

#### 🛠️ What We’ll Cover:

• Foundations of Multi-Agent Systems – Why they outperform single-agent approaches
• Core Architecture Patterns – Subagents, skills, handoffs, and routers explained with practical examples
• Choosing the Right Design – Decision framework for selecting the best LangChain setup
• Agent Skills in Practice – Defining, composing, and invoking modular agent capabilities
• Orchestration & Context Management – Task routing strategies and managing shared context
• Live Demo – Implementing and orchestrating agent skills using LangChain
• Performance Considerations – Real-world trade-offs and scalability challenges

#### 🔍 Why Attend?

• Build scalable multi-agent systems for complex, real-world tasks
• Understand practical design patterns and architectural trade-offs
• Experience live demonstrations beyond slide-based sessions
• Leave with actionable guidance you can apply immediately