Mastra Workshops
Join the Mastra team and expert guests for live, hands-on workshops that teach you how to build and deploy AI agents and applications.
Upcoming Workshops
Past Workshops
2 days ago
45 minutesBuild agentic workflows with Mastra
NA
Last week
1 hourBuild and deploy your first agent with Mastra
2025 might be the year of AI agents but this session is your chance to actually build and deploy an agent yourself. AI agents are autonomous systems that can perceive their environments, make decisions, and independently take actions to achieve specific goals. With today’s tools and frameworks, it’s never been easier to build them, and Alex at Mastra how to do it in less than an hour. Use agents to build things like a personalized travel agent that puts together vacations for you. Or use multiple-agents to simulate a ‘team’ of writers and editors that seamlessly collaborate on content. This event is open to all devs and aspiring AI engineers, regardless of background, so feel free to share the invite link. It’s recommended that you have a code editor and node v20+ installed prior to the session. You should be comfortable with basic JavaScript and the command line.This isn’t a talk; it’s a live workshop where you’ll walk away having built and deployed your first AI agent.
Last week
1 hourBuild agents that never forget with Mastra
Agent memory is the difference between chatbots that forget everything and AI assistants that truly understand you. This workshop will teach you how to implement Mastra's newly improved memory system that achieved 80% accuracy on the LongMemEval benchmark - outperforming other frameworks by 8 points. We'll cover both types of memory in Mastra: working memory for tracking user preferences and characteristics, and semantic recall (RAG) for long-term conversation history. You'll learn the practical techniques we discovered while spending $8k and burning through 3.8 billion tokens to optimize these systems. Build agents that remember user preferences across sessions, recall relevant context from months of conversation history, and handle temporal reasoning correctly. We'll walk through real implementation examples including how to configure memory templates, optimize retrieval settings, and format recalled information for better LLM understanding. You'll learn why RAG is very much alive for agent memory (despite claims otherwise), when to use working memory versus semantic recall, and how proper formatting can dramatically improve accuracy. We'll also cover the performance considerations and cost optimizations that matter in production. This event is open to all devs and aspiring AI engineers, regardless of background, so feel free to share the invite link. It's recommended that you have a code editor and node v20+ installed prior to the session. You should be comfortable with basic JavaScript and the command line. This isn't a talk; it's a live workshop where you'll walk away with agents that have state-of-the-art memory capabilities.
October 2, 2025
1 hourUnderstanding Mastra's new streaming architecture
Join Abhi (co-founder and CTO) and Ward (Principal Software Engineer) for an informative workshop where we will dive into the recent updates to Mastra's streaming architecture. With the release of @mastra/core v0.19.0, our new streaming protocol has become the default experience, introducing significant changes designed to enhance the functionality and compositional capabilities of AI applications. What You Will Learn: The rationale behind the transition to our custom streaming layer, moving away from reliance on Vercel's AI SDK. An in-depth look at the streamVNext and generateVNext functions, now promoted to the primary stream and generate functions. How the updated functions handle nested agent calls, long-running tools, and complex orchestration patterns. The benefits of adopting the new streaming format options, such as 'aisdk', and what this means for frontend compatibility. Guidance on migrating from the original functions, with insights into the provided Legacy variants. Who Should Attend: This workshop is ideal for developers currently using Mastra, especially those who have been working with the vNext functions or are planning to transition from the original streaming functions. Whether you're looking to understand the new architecture or need assistance with migration, this session will provide valuable insights.
September 18, 2025
1 hourBuild Production-Ready RAG Applications with Mastra
Retrieval Augmented Generation (RAG) has become essential for building AI applications that can effectively leverage your data. In this hands-on workshop, you'll learn how to build sophisticated RAG systems that go beyond basic implementations. Learn the proven techniques that make RAG systems reliable and effective, including optimal chunking strategies, modern retrieval methods, and hybrid search approaches that combine the best of semantic and keyword search. Join Mastra.ai to understand the architectural decisions that can make or break your RAG application's performance. You'll get hands-on experience implementing: Evaluating when RAG is needed vs. when context windows suffice Advanced document chunking strategies for different content types Sophisticated semantic search and embedding techniques Hybrid retrieval systems combining keyword and semantic search Re-ranking strategies to improve result relevance Performance optimization techniques for production environments This workshop is ideal for developers and AI engineers who want to build more sophisticated RAG applications. Participants should have familiarity with JavaScript and understand fundamental RAG concepts. Come prepared with a code editor—you'll leave with working implementations of advanced RAG components that you can integrate into your projects. Move beyond basic RAG implementations and learn how to build systems that can handle real-world complexity. Join us for this practical session where you'll implement production-ready RAG solutions using proven architectural patterns.
September 11, 2025
1 hourMaster AI Evaluation: Build and Run Evals with Mastra
2025 is seeing explosive growth in AI applications, but how do you know if they're actually performing well? This hands-on workshop will teach you how to build and run comprehensive evaluation frameworks for your AI systems. Evaluating AI systems is crucial for ensuring reliability, safety, and performance at scale. Join Mastra.ai to learn practical strategies for implementing evals that give you confidence in your AI deployments. You'll learn how to use to assess your AI application and AI Agent capabilities, detect potential issues, and maintain high standards of quality. Get hands-on experience with essential eval strategies including: - Implementing LLM-as-judge evaluation frameworks - Setting up automated evaluation pipelines - Creating targeted test cases for your specific use cases - Monitoring and analyzing eval results through AI ops This workshop is perfect for anyone building an AI Agent or AI application. Basic familiarity with JavaScript is recommended, and participants should have a code editor ready. You'll walk away with working eval implementations and practical knowledge you can immediately apply to your AI projects. Don't just deploy AI—deploy it with confidence. Join us for this practical, hands-on session where you'll build real evaluation frameworks that you can start using right away.
September 4, 2025
1 hourBuild an MCP Server with Mastra
If you have been looking for an opportunity to get hands-on with MCP server development, this is it! The Model Context Protocol allows AI applications to connect to external resources, and Mastra makes building your own server straightforward. This session is your chance to learn MCP server creation using Mastra. You'll learn the fundamentals of MCP, discover how to build a custom server from scratch, and see how to deploy it for real-world use. Together we will go through the entire process in less than an hour. Build a server that can expose your custom tools and resources to any MCP-compatible client, from Claude Desktop and Cursor to other popular clients. You'll understand the MCP specification, implement server endpoints, and test your creation with live client interactions. This event is open to all devs and aspiring AI engineers, regardless of background. You will get access to all the code so it's recommended that you have a code editor and node v20+ if you want to test it out. You should be comfortable with basic JavaScript and the command line. This isn't a talk; it's a live workshop where you'll walk away knowing how to build and deploy a real MCP server.
August 28, 2025
1 hourBuild Agentic Workflows with Mastra
2025 has seen AI agents evolve rapidly, but orchestrating complex AI operations remains a challenge. This session is your chance to master Mastra's new and improved workflow system to create sophisticated, multi-step AI processes that actually work in production. Workflows in Mastra help you orchestrate complex sequences of operations with powerful features like branching, parallel execution, and state management. The Mastra team will show you how to build resilient, observable AI workflows in less than an hour. Use workflows to create systems like a content generation pipeline that coordinates research, writing, and editing steps. Or design an AI recruiting workflow that gracefully handles user input, database lookups, and external API calls while maintaining context throughout the process. This event is open to all devs and aspiring AI engineers, regardless of background, so feel free to share the invite link. You should be comfortable with basic JavaScript and the command line.
July 31, 2025
1 hourBuilding Agents with Mastra Templates
Getting started with AI agents shouldn't require building everything from scratch. This workshop introduces Mastra Templates, a new feature that lets you quickly spin up working examples of agents, workflows, and MCP servers with a single command. We'll show you how to use Mastra Templates to instantly begin iterating on pre-built agent examples. Whether you need a customer support agent, a data analysis workflow, or a custom MCP server, you'll learn how to get up and running in minutes instead of hours. You'll also discover how to deploy these templates directly to Mastra Cloud with one-click deployment, taking your local experiments to production without complex configuration. We'll walk through the entire process from template selection to live deployment. Finally, we'll cover how to create your own Mastra Templates. Learn the template structure, best practices for making reusable components, and how to share your templates with the community. Whether you're building internal tools or open-source examples, you'll understand how to package your work for others to use. This workshop combines practical demonstrations with hands-on building time. You'll leave with working agents deployed to the cloud and the knowledge to create templates that accelerate your future AI projects. This event is open to all devs and aspiring AI engineers, regardless of background, so feel free to share the invite link. It's recommended that you have a code editor and node v20+ installed prior to the session. You should be comfortable with basic JavaScript and the command line. This isn't a talk; it's a live workshop where you'll walk away with deployed agents and your own custom templates ready to share.