Agentic AI Masterclass: OpenAI, Claude, LangGraph & Vercel

Course Overview

This course teaches how to build 10 complete, full-stack AI agent applications using TypeScript, Next.js, and modern production tooling. It covers building agents with OpenAI Agents SDK, Claude Agent SDK, LangGraph, and Vercel AI SDK, including advanced features like multi-agent handoffs, Retrieval-Augmented Generation (RAG), stateful workflows, and secure authentication. Students will learn to create applications similar to ChatGPT, Perplexity, and NotebookLM, integrating streaming responses, web search, image generation, and more.

Key Takeaways

• Build AI agents with OpenAI Agents SDK featuring tool calling, multi-agent handoffs, and guardrails.
• Create terminal coding assistants and autonomous GitHub pull request reviewers using Claude Agent SDK.
• Implement Retrieval-Augmented Generation with embeddings, Pinecone vector search, and source-backed answers.
• Design stateful agent workflows with LangGraph and manage long-running background jobs with Inngest.
• Develop ChatGPT and Perplexity-style apps using Vercel AI SDK with streaming, web search, and image generation.
• Write a custom agent SDK including tools, memory, planning, streaming, tracing, guardrails, and handoffs.
• Add secure authentication using Better Auth and Clerk, and manage data with Prisma, Drizzle, Neon Postgres, and MongoDB.

Prerequisites

Basic knowledge of TypeScript and Next.js is implied for following the course content effectively.

Target Learners

Developers interested in building advanced AI agent applications, integrating multiple AI SDKs, and creating production-ready AI-powered web applications using modern JavaScript/TypeScript frameworks and tools.