Data Science Dojo- Phoenix

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

As generative AI systems continue to advance, traditional diffusion models often introduce complexity through iterative denoising and carefully tuned noise schedules. Flow Matching offers a more intuitive alternative by learning continuous transformations that move noise directly toward data, enabling faster sampling and simpler training.
In this session, we’ll introduce the fundamentals of Flow Matching and explain how it differs from diffusion-based approaches in both theory and practice. You’ll gain a clear understanding of why this method is gaining traction in state-of-the-art systems such as Stable Diffusion 3 and Meta’s Movie Gen, and where it fits in the broader generative AI landscape.
Through visual explanations and a hands-on code walkthrough, we’ll demonstrate how a model can be trained from scratch to transport noise into structured data. By the end of the session, you’ll have a solid conceptual foundation and practical starting points for exploring this approach in your own generative AI projects.

## 🛠️ What We’ll Cover:

• Core Concepts – An intuitive explanation of Flow Matching and how it compares to diffusion models
• Modeling Approaches Compared – Strengths, trade-offs, and why straight transport paths improve efficiency
• Real-World Use Cases – Applications in image generation, video synthesis, audio modeling, and molecular design
• Key Mechanics – Velocity fields, continuous flows, and simplified training objectives
• Hands-On Demo – A step-by-step notebook walkthrough using a toy dataset with visualized particle movement
• Efficiency Benefits – Reduced sampling steps, simpler objectives, and maintained output quality
• Getting Started – Recommended papers, tools, and libraries to begin experimenting

## 🔍 Why Attend?

• Understand modern generative modeling beyond traditional diffusion methods
• Learn how newer approaches improve efficiency without added complexity
• See practical, code-driven explanations instead of purely theoretical slides
• Leave with clear guidance and resources you can apply immediately