Your #1 platform for tech & programming education

Learn ai and modern development by building real projects

Hands-on video courses where every line of code is typed and explained, with quizzes, source code and captions.

Browse course Let’s talk
banner

Leading the way in software Development

Far far away, behind the word mountains, far from the away countries vokalia and consonantia, there live the blind texts. separated they live in bookmarksgrove right at the coast of the semantics, a large language ocean.

  • - Education award achived
  • - Available online courses
Learn more

Explore Categories

View all
TypeScript
Next.js

Pick a course to Get started

The industry standard dummy text ever since the unknown printer took a galley of type and scrambled

TypeScript

$76

$35

Build an AI Agent with Tools and MCP in TypeScript
Amine Lahmar
(0 Reviews)

Lessons : 51

Students : 0

Last updated Thu, 29-Oct-2026

Build an AI Agent with Tools and MCP in TypeScript
51 Lessons 08:28:48 Hours English
Outcomes:
  • Create a Next.js App Router project in TypeScript with a server-only client for any OpenAI-compatible model.
  • Build a chat route and a streaming chat UI that make real model calls, with clear errors.
  • Define typed tools with Zod and reject invalid arguments from the model before anything runs.
  • Write an agent loop that offers tools, runs the one the model picks, returns results and stops at a step limit.
  • Build an MCP server in TypeScript with the official SDK (@modelcontextprotocol/server) and test it with the MCP Inspector.
  • Connect a Next.js app to your MCP server as an MCP client (@modelcontextprotocol/client) and switch the agent to its tools.
  • Add a human approval step before any change, enforced on the server with one-time approval tokens and an audit log.
  • Add memory, timeouts, retries and a cost budget, then evaluate the agent with a Vitest suite.
  • Run the app and MCP server in production and apply the security checklist for MCP servers.
Remove from cart Add to cart
Next.js

$75

$35

Build a Chatbot with Next.js and an OpenAI-compatible API
Amine Lahmar
(0 Reviews)

Lessons : 27

Students : 0

Last updated Thu, 29-Oct-2026

Build a Chatbot with Next.js and an OpenAI-compatible API
27 Lessons 05:24:38 Hours English
Outcomes:
  • Create a new Next.js project with TypeScript and run it locally (npm run dev).
  • Write a client-side chat UI using React components under the App Router.
  • Implement a server-side API route that calls an OpenAI-compatible API using the openai npm client ([email protected]).
  • Send user messages to the server route, receive model responses, and render them in the UI.
  • Use TypeScript types to model request and response shapes for safer code and clearer errors.
  • Handle basic errors and show user-friendly messages when the AI API fails or the network drops.
  • (Optional) Implement streaming responses so message text appears progressively.
  • Persist chat history to localStorage and understand how to swap that for a simple server DB later.
  • Deploy the app to Vercel (or another host) while keeping API keys secret.
Remove from cart Add to cart
View more

Frequently asked Questions

WCODS is an academy for AI technology and professional technical education. Our courses teach by building: each course follows one real project from the first file to a working application.

Each lesson is a video in which the code is typed and explained line by line. Courses include quizzes, the full source code and captions, so you can follow along at your own pace.

It depends on the course. Each course page lists its level and its requirements under "Requirements", so you know exactly what to have in place before you begin.

Yes. Many courses have a free introduction lesson that shows what the course covers and how it is taught. Look for the free preview on the course page.

Once you are enrolled, you can watch the course as often as you like for as long as it is offered on WCODS.

See more

What our Customers say

Having enjoyed a breathlessly successful 2015, there can be no dj dynamic set of teaching tools built to be deployed.