← back
[Workshop] AI Pipelines and Agents in Pure TypeScript with Mastra.ai — Nick Nisi, Zack Proser
Original: [Workshop] AI Pipelines and Agents in Pure TypeScript with Mastra.ai — Nick Nisi, Zack Proser
Takeaway
Mastra lets TypeScript devs build production AI pipelines with strongly-typed workflows and a single-stack alternative to Python frameworks.
Summary
- WorkOS-led workshop building an AI meme generator in TypeScript using Mastra: workflows (typed pipelines with Zod validation/coercion), tools (functions agents call), and agents (LLM + tools + prompt).
- Mastra ships batteries-included: playground, persistence, memory, observability, evals — pitched as production-ready, not toy code.
- Walked through MCP as Anthropic-originated open standard now adopted across Claude, Cursor, Windsurf, OpenAI; in the final build they had the agent call a workflow rather than individual tools.
- Emphasis on Zod for runtime coercion of LLM output into reliable schemas and on workflows as the deterministic backbone wrapped by the non-deterministic agent.
mastratypescriptagents
Original description
This hands-on workshop introduces Mastra.ai, a TypeScript framework that streamlines the development of agentic AI systems compared to traditional approaches using LangChain and vector databases. Participants will learn to build structured AI workflows with composable tools and reliable control, enabling them to create internal AI assistants that can handle requests like data cleaning, email drafting, and document summarization with minimal code. The session covers Mastra installation, running a local MCP server, defining tools and agents in TypeScript, using the Mastra playground, and implementing practical examples such as RAG setups and tool-chaining agents—all designed to equip attendees with the skills to develop scalable AI-driven internal tools based on sound software engineering principles rather than just experimental prompts. About Nick Nisi Nick Nisi is an elite software engineer who is a veteran of open source web development, a lover of karaoke, an advocate for diversity in tech, a conference organizer extraordinaire, a lover of new experiences, and a beacon of expertise, kindness and hope for his development team. About Zack Proser Zachary Proser builds AI systems that actually ship. For over thirteen years at Cloudmark, Cloudflare, Gruntwork, Pinecone, and now WorkOS, he’s worked across the stack—from infrastructure to interface—shipping production code. At WorkOS, he shares what he learns in the open: creating sample applications and architectures, technical guides, and real-world lessons that make identity, security, and AI accessible. His posts are known for their copy-paste readiness and refusal to hand-wave. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter