Next batch starts 21 Nov

AI Agents for Professionals

2-day live workshop · prompt engineering, tool calling, n8n, LangChain, Claude and MCP

A two-day live workshop for working professionals. Learn prompt engineering, build AI agents that call tools in n8n, then build them in code with LangChain, Claude and MCP.

Prompt engineering-ல இருந்து n8n, LangChain, Claude, MCP வரைக்கும், ரெண்டே நாள்ல live-ஆ உங்க சொந்த AI agent-ஐ உருவாக்கலாம்.

Get the joining details See the full syllabus

2 full daysfrom the first class to the capstone
2 stages6 modules and 39 topics, in the order you learn them
Live in Tamilwith recordings and notes in English
Hands-onevery topic tried on your own machine

What you will work with

LangChain

Pythonn8nClaudeMCP

By the end, you can

Write prompts that give reliable, structured answers
Explain what an AI agent is and when a simple prompt is enough
Build an agent in n8n that calls tools and finishes a real task
Build an agent in code with LangChain and Claude
Choose the right Claude model for a task based on cost, speed and quality
Connect an agent to outside tools and data with MCP

What you get

Two full live daysSaturday and Sunday, 10 AM to 5 PM IST with breaks, and time to ask questions as they come up.
Build as you learnEvery session ends with something running, so you learn by building and not just by watching.
Four tools in one workshopPrompt engineering, n8n, LangChain with Claude, and MCP, taught in the order they build on each other.

Your path, stage by stage

2 stages, in the order you learn them. Each one has a clear goal and ends with something you build and keep. Every topic runs on your own machine first.

1Day 1 · Prompts and agents in n8n
2Day 2 · Agents in code with LangChain, Claude and MCP

Stage 1 of 2

Day 1 · Prompts and agents in n8n

Write prompts you can trust, understand how agents call tools, and build agents without writing code.

You buildAn n8n agent that calls tools and automates a real workflow
Prompt engineering6 topics

Get reliable, structured answers from a model.
How a model reads your prompt

Tokens and context in plain words
Why models make things up, and how to catch it
Prompts that work

Role, task, context and format
Giving examples in the prompt
Asking for structured JSON output
Testing a prompt on real cases
How AI agents work5 topics

What makes an agent different from a chatbot.
The agent loop

Think, call a tool, read the result, repeat
Tool calling, how an agent decides which tool to use and with what inputs
Memory across steps
Knowing when to use one

A single prompt, a workflow or an agent
Where agents fail and how to keep a human in the loop
Building agents in n8n7 topics

Workflows and agents without writing code.
n8n basics

Triggers, nodes and data between them
Calling an LLM from a workflow
Agents in n8n

The AI Agent node
Giving the agent tools
Adding memory
Handling errors
Hands-on, automate a real task end to end
Stage 2 of 2

Day 2 · Agents in code with LangChain, Claude and MCP

Build agents in code, pick the right Claude model, and connect agents to tools and data with MCP.

You buildAn agent of your own, connected to tools through MCP
LangChain and Claude9 topics

The same agent ideas, now in Python.
Calling Claude from code

Your first API call
System prompts and conversations
Structured output
Which Claude model for which job

Haiku, Sonnet, Opus and Fable compared
Cost, speed and quality
Using effort before changing the model
Agents with LangChain

Defining tools from Python functions
Building the agent
Reading what the agent did, step by step
MCP, the Model Context Protocol5 topics

One standard way to connect agents to tools and data.
Why MCP exists

Clients, servers and tools
Using a ready-made MCP server
Your own server

Building a small MCP server
Connecting it to Claude and to your agent
Keeping access safe
Build your own agent7 topics

Put both days together in one working agent.
Final build

Pick a task from your own work
Design the prompts and tools
Build and connect it through MCP
Before you trust it

Test it on real cases
Control cost
Guard against prompt injection
Show your agent to the group

What you will build

A set of tested prompts for tasks from your own work
An n8n agent that calls tools and automates a real workflow
A LangChain agent on Claude that calls your own Python functions
A final agent of your own, connected to tools through MCP

Who it is for

Working professionals who want to use AI agents in their daily work
Developers who want a fast, practical start with agents
Team leads who need to judge where agents help and where they do not

What our students say

In their own words, from students of our live GoDisai batches.

Kubernetes

Concepts are explained in the simplest way to understand. Doubts are clearly explained on the spot until everyone understands the concept — very useful for preparing for interviews.

HariniJob seeker

Kubernetes

If you want to change your role with the current trend, he is the best — and you can learn in your mother tongue. I can now change my role and attend interviews confidently.

Sathish @ BalaWorking professional

RAG

The way you teach things from absolute scratch and not from an abstraction level really made me understand a lot of technical topics with much more depth. “I am able to explain why and how things work and know how to do it” — that would be the takeaway from the sessions.

Gokul KannanWorking professional

40 Days of RAG

The hands-on examples and doubt-clearing sessions helped me understand how to apply these concepts in my own projects.

Ramya PerumalJob seeker

Django · Backend Mastery

Clear explanation with simple examples and a practical approach to real-time issues. You can learn the basics very clearly and gain the confidence to be a developer.

Arun MadhuWorking professional

System Design

I now have the confidence to crack system design interviews.

Prajin Kumar PStudent · SJIT HOPE