Web Development · WDC-116

AI Next.js Fullstack Workshop

AI Next.js Fullstack Workshop is a developer workshop in building a structured workflow with AI agents, from AI-assisted UI design, MCP and spec-driven development to Next.js with TypeScript, Prisma, Supabase, Better Auth and AI code review. It suits web developers and frontend developers moving into backend work, and you leave able to deploy a web app to production.

Updated
From 5,310 THB / person 5,900 −10% excl. VAT 7% · group rates available
PDFDownload the course outline
  • Duration6 hours · 1 days
  • FormatOnsite / live online
  • Next round21 Dec 26
  • CertificateIncluded

Course overview

Most developers already use AI to help write code, but they use it one question at a time and paste the results in. That captures only part of the value and usually produces code that does not fit the existing structure. Working with AI professionally requires an explicit workflow: design first, write a spec that keeps the AI inside a defined frame, then delegate work in pieces and review what comes back. This full-day workshop is for people who

already have web fundamentals and want to assemble that complete modern workflow. It covers AI-assisted UI design, connecting the design into the editor through MCP, spec-driven development with design.md and spec.md, planning and breaking down work with AI, building the app with Next.js and TypeScript alongside Prisma and Supabase, adding authentication, debugging and code review with AI, delegating iterative work to an AI agent, and deploying to production with the right configuration. (1 day, 6 hours, Intermediate level.)

What you’ll gain

  • Assemble a complete AI-assisted development workflow from design to deployment
  • Use AI to design UI and evaluate the output before building on it
  • Bring the design into the editor with MCP to generate starting code quickly
  • Write spec files that keep AI output aligned with the design
  • Plan the project and break work into pieces with AI so development keeps moving
  • Build a web app with Next.js and TypeScript alongside Prisma and Supabase
  • Implement authentication and user permissions in the application
  • Use AI systematically for debugging and code review
  • Deploy to production with environment variables and secrets handled safely

Who this course is for

  • Web developers who want to make their AI-assisted work systematic
  • Frontend developers moving into backend and database work
  • Anyone with HTML, CSS and JavaScript fundamentals who wants to start with Next.js
  • Freelancers and project owners who need to ship faster without losing quality
  • Development teams standardizing how their people work with AI

Prerequisites

  • HTML, CSS and JavaScript fundamentals sufficient to read and edit code
  • Experience building a web page or small web app (Next.js experience not required)
  • Basic command line and Git skills
  • Bring your own laptop (Windows or macOS) with permission to install software

Curriculum

Course Details

A 1-day course, 6 hours (10:00-17:00), run as a hands-on workshop throughout. Intermediate level; learners should already have HTML, CSS and JavaScript fundamentals and must bring their own laptop (Windows or macOS) with permission to install software. Learners take home the source code, a spec template set (design.md and spec.md), a prompt workflow, and their own application already deployed to production. The content focuses on workflow and principles, so it transfers to other AI tools as the technology changes.

Session 1: AI UI Design, MCP and Spec (10:00-12:00)

Section 1 AI-Assisted UI Design
  • Using AI to draft screens and produce design alternatives quickly
  • Evaluating AI-generated design: consistency, real usability and buildability
  • Establishing a color system and component set so every screen stays coherent
  • Lab: design your project screens with AI and pick the direction to build
Section 2 MCP, Bringing Design into the Editor
  • What MCP is and how it lets an AI agent reach external tools and data
  • Passing the design into the editor to generate starting code instead of from scratch
  • Reviewing and adapting the generated code to fit the real project structure
  • Lab: connect your design into the project and get your first screen scaffold
Section 3 Spec-Driven Development
  • Why one-question-at-a-time prompting produces code that does not fit the codebase
  • Writing design.md to describe the look and behaviour of the system for the AI to read first
  • Writing spec.md to define scope, requirements and acceptance criteria per task
  • Lab: write design.md and spec.md for your project and have the AI follow them

Session 2: Planning and Next.js Fullstack (13:00-15:15)

Section 4 Project and Task Planning with AI
  • Having AI plan the project and order the work from the spec you wrote
  • Breaking large work into pieces the AI can finish in one pass
  • Sequencing tasks so development keeps moving without getting stuck
  • Tracking progress and adjusting the plan when requirements change
Section 5 Next.js and TypeScript
  • Next.js project structure and the split between server and browser work
  • Routing, building APIs and fetching data for display
  • Using TypeScript to reduce errors and give the AI a clearer view of the code
  • Lab: scaffold a Next.js project with your first screens and API routes
Section 6 Databases with Prisma and Supabase
  • Designing the data model and the relationships between tables
  • Using Prisma to define the schema and manage structural changes
  • Connecting Supabase and reading and writing data from the app safely
  • Lab: build your project database and wire it into the screens you made
Section 7 Authentication and User Permissions
  • Building signup and login with Better Auth
  • Managing sessions and protecting pages that require login
  • Defining user roles and checking permissions on the server side
  • Lab: add login and restrict access in your own application

Session 3: AI Debugging, Agents and Production Deploy (15:15-17:00)

Section 8 Debugging and Code Review with AI
  • Giving the AI enough context that it can actually find the cause
  • Having AI review code and flag security and performance risks
  • The limits of AI review and where a human still has to decide
  • Delegating work to an AI agent in iterations and reviewing each round
Section 9 Deploying to Production and Wrap-up
  • Preparing the project for deployment and the checks to run first
  • Setting environment variables and storing secrets safely
  • Connecting the production database and updating the app after deployment
  • Workshop: deploy your app to production and plan how to apply this workflow

Schedule & training options

For individuals — public rounds

21December
Classroom21 Dec 26
20 seats left
1February
Classroom1 Feb 27
20 seats left
5April
Classroom5 Apr 27
20 seats left
7June
Classroom7 Jun 27
20 seats left
2August
Classroom2 Aug 27
20 seats left
4October
Classroom4 Oct 27
20 seats left
8December
Classroom8 Dec 27
20 seats left

For organisations — in-house / private

  • Tailor the content to your team’s tools and projects
  • Your dates, at your office or live online
  • Quotation with tax ID for procurement
Corporate training quote

Instructors

Frequently asked questions

What is MCP, and how does it let an AI agent do more?

MCP (Model Context Protocol) is an open standard that lets AI applications connect to external tools and data sources, such as design tools, databases or APIs, through MCP servers in a consistent way. Instead of you copying data into a chat, the agent can read designs or real data and act on them, for example pulling a design into the editor to generate starter code. Grant only the access it needs.

What are the steps for spec-driven development with AI?

Start by writing design.md to describe how the system looks and behaves, then spec.md to set the scope, requirements and acceptance criteria for each piece of work. Have the AI read both before it starts, help plan and break the work into chunks it can finish in one pass, check each round against the acceptance criteria, and update the spec when requirements change. The code fits the existing structure far better than one-off prompts.

How does Prisma help manage the database in a Next.js project?

Prisma is a TypeScript ORM: you define tables and relationships in a schema.prisma file and it generates a fully typed client for you. When you write queries, the editor autocompletes them and warns you about wrong field names. When the schema changes, prisma migrate creates migration files so the database structure changes in a controlled way, and it works with PostgreSQL on Supabase.

Who is the AI Next.js Fullstack Workshop for, and what should I know beforehand?

It suits web developers who want a structured way of working with AI, frontend developers moving into backend and database work, people with HTML, CSS and JavaScript who want to start with Next.js, and freelancers who want to deliver faster. You should be able to read and edit HTML, CSS and JavaScript, have built a small website before, and use the command line and Git at a basic level. Next.js experience is not required.

What will I be able to do after the AI Next.js Fullstack Workshop?

You will be able to design screens with AI and bring them into the editor via MCP, write design.md and spec.md for the AI to follow, build a Next.js app in TypeScript with an API, design the database with Prisma and Supabase, add login and user roles with Better Auth, use AI for debugging and code review, and deploy the app to production. Participants who complete the training receive a Certificate of Completion with its own number, which can be verified online.

What do I need to bring to the AI Next.js Fullstack Workshop?

Bring your own Windows or macOS laptop with permission to install software, as you will install development tools and run a Next.js project on your own machine throughout the workshop. It is worth refreshing your JavaScript, command-line and basic Git skills beforehand so you can keep pace with the labs from the start.