AI and machine learning · Free online course

Generative AI and LLM Foundations

What a language model is actually doing when it answers, why it is confidently wrong sometimes, how to call one from Python on a free route, how to run one privately on your own laptop, and how to test one before you trust it with a datasheet. The concept course under the whole AI track.

13 modules
10h 31m of video
Beginner
English
₹0, free

Generative AI and LLM Foundations course cover

₹0Free for good

Worth ₹5,999 by length and depth against classroom training. It has always been free; that is not a former price.

No card. Checkout takes a minute and gives you a receipt.

Overview

About Generative AI and LLM Foundations

Generative AI and LLM Foundations is a free, self-paced online course from EDWartens for engineers, developers and students applying AI to real work. It has 13 modules and 10h 31m of video lessons by Microsoft Developer, 3Blue1Brown, Andrej Karpathy and others, with written notes and worked problems, a practical project with a document pack and a 15-question final assessment (pass mark 60%). Learning is free with an account; an optional certificate with a public verification code is issued when you pass. Last updated 27 September 2026.

Who it is for: Engineers, developers and students applying AI to real work

This course includes

10h 31m of video lessons
13 modules with written notes and diagrams
One final assessment: 15 questions, pass mark 60%
Ask-an-engineer support from practising engineers
Lifetime access, the course does not expire
Optional verifiable certificate when you finish

Step 1 of 3
Learn the 13 modules
10h 31m of video lessons, written notes and a practice task per module, at your own pace.
Step 2 of 3
Pass the final assessment
15 questions drawn from every module, pass mark 60%, 3 attempts.
Step 3 of 3
Take the certificate, if you want it
Optional, paid once, only if you choose it. The course stays free either way.
See the certificate and its price

A look inside

Generative AI and LLM Foundations: Syllabus at a glance — Syllabus at a glance

Generative AI and LLM Foundations: What you will be able to do — What you will be able to do

Generative AI and LLM Foundations: Tools and credits — Tools and credits

From the lessons

What generative AI is, and what it is not
by Simplilearn
How the models are built: Karpathy's introduction
by Andrej Karpathy
Using it responsibly in a plant
by Microsoft Developer
Calling a model from Python
by Microsoft Developer
Embeddings, vector search and the idea of RAG
by IBM Technology
Prompting, RAG or fine-tuning; images and low-code
by Microsoft Developer

Lesson frames belong to the creators named in the Credits and are shown from YouTube.

What you learn

What you will be able to do

Explain tokens, context windows, training and hallucination in plain words; choose between hosted and local models for a job; write a structured prompt with a NOT FOUND rule; call free models through the OpenRouter API and run open models with Ollama; understand embeddings, RAG, function calling and agents; and evaluate an assistant with a proper test set.

Explain in plain words what an LLM does when it answers, and why it hallucinates
Choose a model for a job: context length, JSON output, local or hosted, licence
Write a prompt with role, task, context, format and a NOT FOUND rule
Call a free model from Python through OpenRouter, with retries and JSON output
Run an open model privately on your own laptop with Ollama and a Modelfile
Build a datasheet assistant and measure its accuracy and refusal rate with a real test set

Syllabus

Course content, module by module

In order, at whatever pace suits you. Each module ends with a practice task that builds on the last.

Modules: 13
Video lessons: 34
Of video: 10h 31m
Final questions: 15

01
What generative AI is, and what it is not
3 lessons · 27m
02
How an LLM works: tokens in, probabilities out
4 lessons · 24m
03
How the models are built: Karpathy's introduction
1 lesson · 60m
04
Choosing a model: hosted, local, open and free
2 lessons · 33m
05
Using it responsibly in a plant
3 lessons · 28m
06
Prompting fundamentals
2 lessons · 41m
07
Calling a model from Python
2 lessons · 29m
08
Running a model on your own machine with Ollama
5 lessons · 42m
09
Embeddings, vector search and the idea of RAG
4 lessons · 46m
10
Function calling, agents and the application lifecycle
4 lessons · 43m
11
Prompting, RAG or fine-tuning; images and low-code
3 lessons · 1h 0m
12
The datasheet assistant, tested
1 lesson · 3h 19m
13
Final assessment
0 lessons · 0m
Final assessment · 15 questions, pass mark 60%

Show all 13 modules

Project

The course project

Optional practice that ends in the kind of job the course prepares you for, with the documents that go with it.

About 5 hours

Build a datasheet assistant on a free model, and measure how often it is wrong

Three public datasheets, one free language model, fifteen test questions with answers you have verified yourself. The deliverable is not the chatbot; it is the evaluation table that says how accurate it is and how often it invents an answer.

Sample document pack, 7 documents, filled in for the scenario

PlanEvaluation Plan: Datasheet Assistant Pilot
RegisterSource Document Register
RegisterTest Set: Fifteen Questions with Verified Answers
SDSAssistant Design: Prompt, Model and Call
Test reportEvaluation Results: Run 1 and Run 2
Risk registerRisk Register: Datasheet Assistant on the Intranet
ReportRecommendation to the Managing Director

Read inside the course and download as a workbook. The project is optional practice, marked when you submit it; the certificate needs only the modules and the final assessment.

About 3 hours

Hosted versus local: the same ten engineering prompts through two models

Run ten realistic engineering prompts through a free hosted model on OpenRouter and a small local model in Ollama (or a second free hosted model if your laptop cannot run Ollama). Score them side by side and decide which jobs belong where.

Sample document pack, 7 documents, filled in for the scenario

PlanComparison Plan: Hosted versus Local Model for Daily Engineering Work
RegisterPrompt Set and Marking Keys
ProcedureSet-up and Run Procedure for Both Routes
Test reportComparison Results: Ten Prompts, Two Routes
RegisterFailure Log with Corrected Answers
ReportRecommendation: Which Work Goes Local, Which Stays Hosted
RegisterData Classification for Model Use

Read inside the course and download as a workbook. The project is optional practice, marked when you submit it; the certificate needs only the modules and the final assessment.

Tools

Software, hardware and lessons

Software

Google Colab, a free OpenRouter key, optionally Ollama on your own laptop. No paid account anywhere.

Hardware

None required. A laptop with 8 GB RAM runs the optional local models.

Who it is for

Beginner. No coding needed for eight of the twelve modules; basic Python (the Python for AI course, or equivalent) for the API and project modules.

Video lessons by

Microsoft Developer
3Blue1Brown
Andrej Karpathy
IBM Technology
codebasics
Tech With Tim
Amit Thinks
KodeKloud
Simplilearn
edureka!

Independent creators, credited in full under Credits.

Software you need

What to download, where from, what it costs and how to install it. Every link goes to the maker's own site, never a mirror.

Required

01
Google Colab
Google, in the browser
Free, GPU time not guaranteed
Runs on
Any modern web browser
Account
A free Google account
Colab is free to use. In the free version GPUs and TPUs are heavily restricted and not guaranteed, sessions can run for at most 12 hours, and idle sessions are stopped. Paid plans give more reliable access.
Show the 4 stepsHide the steps
Steps
1. 1.Open colab.research.google.com and sign in with your Google account.
2. 2.Click New notebook (or open the notebook your course links to).
3. 3.For a GPU, choose Runtime, then Change runtime type, then pick a GPU if one is offered.
4. 4.Type code in a cell and press Shift and Enter to run it.
- Save a copy to your Google Drive so your changes are kept.
- Files on the runtime are deleted when the session ends. Save outputs to Drive.
Open Google Colabcolab.research.google.com
02
OpenRouter
OpenRouter, Inc., in the browser
Free models with rate limits
Runs on
Any modern web browser (API works from any language)
Account
A free OpenRouter account
Models with IDs ending in :free cost nothing but are limited to 20 requests per minute and 50 requests per day. Buying at least 10 credits raises the daily free-model limit to 1,000 requests.
Show the 4 stepsHide the steps
Steps
1. 1.Open openrouter.ai and sign up.
2. 2.Go to Keys in your account settings and create an API key. Copy it somewhere safe.
3. 3.Pick a model whose ID ends in :free.
4. 4.Call it with any OpenAI-compatible client using the base URL https://openrouter.ai/api/v1 and your key.
- Never paste your API key into shared code or public repositories.
- The list of free models changes over time. Check the model page before a class.
Open OpenRouteropenrouter.ai

Optional

Useful, not needed to finish the course.

03
Ollama
Ollama Inc.
Free
Runs on
macOS 14 Sonoma or later, Windows 10 or later, Linux
Account
None needed
Ollama is free and open source (MIT licence). Each model you download has its own licence; check it before commercial use.
Show the 4 stepsHide the steps
Steps
1. 1.Open ollama.com/download and pick your system.
2. 2.On Windows run OllamaSetup.exe; on macOS open the DMG; on Linux run: curl -fsSL https://ollama.com/install.sh | sh
3. 3.Open a terminal and run a small model, for example: ollama run <model name> (browse names on ollama.com).
4. 4.Type a question at the prompt. Type /bye to exit.
- Models are several GB each. Check your free disk space first.
- More RAM, or a supported GPU, lets you run larger models faster.
- On Windows you can also install from PowerShell: irm https://ollama.com/install.ps1 | iex
Official download pageollama.com

Checked against each maker's own page on 27 September 2026. Trial lengths and editions change; the maker's page is the final word.

What you walk away with

Your certificate for Generative AI and LLM Foundations

Finish the course, pass the final, and this is the document with your name on it.

Sample EDWartens Certificate of Completion for Generative AI and LLM Foundations — Sample. The issued certificate carries your name, admission number, a unique certificate number and its own QR code.

Verifiable by anyone
A unique certificate number and a public verification page. A recruiter checks it in ten seconds.
Adds to LinkedIn in one click
Issuer, credential ID and URL prefilled, with 5 matching skills to pin to your profile.
QR code on the certificate
Scans straight to the verification page, so a printed copy proves itself.
Names what you can do
Lists the topics covered, from how large language models are trained and how they predict tokens to building and testing a document question-answering assistant.
A permanent link
Put it on a CV, a portfolio or an application. The URL never changes.
Earned, not attended
Issued only after every module and a final assessment at 60%, with 3 attempts. That is why it stands up.

Learning is free. The certificate is optional.

Add it now and pay only when you have finished the course, or come back for it later. One-off, US$23.99, with a receipt.

Issued by EDWartens India (Wartens Automation Private Limited) as a Certificate of Completion for this self-paced course. It is not a vendor certification, a university award or a CPD-accredited activity, and it does not certify competence on live equipment. Delivered electronically; see the refund policy.

FAQ

Common questions

Do I need to code?

Not for most of it. Eight modules are concepts you can follow with no code at all. The API, Ollama and project modules use short Python snippets that are given to you; if you have never coded, do the Python for AI course alongside.

Do I need a paid ChatGPT or OpenAI account?

No. The course uses OpenRouter's free models, which need only a free key and no card, and Ollama for local models, which is free and runs on your own machine.

What is the project in the Generative AI and LLM Foundations course?

You build the simplest assistant that answers questions from three public datasheets on a free model, then test it with fifteen questions you have verified yourself — including five it cannot know — and report its accuracy and how often it invents an answer. A second, shorter project compares a hosted model with a local one.

Is the Generative AI and LLM Foundations course really free?

Yes. Every module, practice task, project and assessment. You create an account so your progress is saved and the assessments can be marked. The certificate is the only paid item, and only if you want it.

What certificate does the Generative AI and LLM Foundations course give?

An EDWartens Certificate of Completion, issued when you have finished the modules and passed the final assessment (the project is optional practice), with a verification code anyone can check. It is not a vendor credential and is never described as one.

Who made the video lessons in the Generative AI and LLM Foundations course?

The creators named in the Credits block at the foot of this page, on their own YouTube channels. EDWartens did not make the videos and the creators are not affiliated with EDWartens. What EDWartens wrote is the study plan, the notes, the practice tasks, the projects and the assessments.

How long does the Generative AI and LLM Foundations course take?

Plan on about 16 hours in all, including the video lessons, notes and practice tasks. It is self-paced, so you work through the thirteen modules at your own speed.

Is the Generative AI and LLM Foundations course free in India, and what does the certificate cost?

Yes. Learning costs ₹0 in India: every module, the written notes, the practice tasks and the final assessment, with no card and no trial period. The only paid item is the optional EDWartens Certificate of Completion, ₹499 including GST for this beginner course, paid in rupees through Razorpay, and only if you want it after passing the final assessment.

All course facts

Price: ₹0, free for good. No trial, no card. Comparable classroom training of this length costs about ₹5,999.
Who it is for: Engineers, developers and students applying AI to real work
Format: 13 self-paced modules, 10h 31m of video, written notes, a practice task per module and one final assessment.
Level: Beginner. Beginner. No coding needed for eight of the twelve modules; basic Python (the Python for AI course, or equivalent) for the API and project modules.
Brand: Vendor-neutral
Software: Google Colab, a free OpenRouter key, optionally Ollama on your own laptop. No paid account anywhere.
Hardware: None required. A laptop with 8 GB RAM runs the optional local models.
Certificate: Optional EDWartens Certificate of Completion, verifiable by code. Not a vendor credential.
Video lessons by: Microsoft Developer, 3Blue1Brown, Andrej Karpathy, IBM Technology, codebasics, Tech With Tim, Amit Thinks, KodeKloud, Simplilearn, edureka! (independent creators, credited below)
Language: English
Last updated: 27 September 2026

PLC programming · FreeSiemens TIA Portal

Siemens TIA Portal in Three Hours free course cover

PLC programming · FreeSiemens TIA Portal in Three Hours

TIA Portal: Build a Machine free course cover

PLC programming · FreeTIA Portal: Build a Machine

Instrumentation for PLC Engineers free course cover

Instrumentation · FreeInstrumentation for PLC Engineers

More free courses: Free AI courses for engineers · Free generative AI and ChatGPT courses

Learning paths with this course

AI foundations for engineers · 4 courses

Classroom course, Bangalore

PLC training in Bangalore

The Automation Engineer Program (AEP) is our classroom course in PLC programming and industrial automation, taught in person at our Electronic City centre.

Credits

Who made the video lessons

The video lessons in this course were created by the people below, not by EDWartens. Every lesson streams from its creator's own YouTube channel; EDWartens neither hosts nor sells that footage, and the creators are not affiliated with EDWartens and do not endorse this course. What EDWartens wrote is the study plan, the notes, the practice tasks and the assessments.

Microsoft Developerthe Generative AI for Beginners series
3Blue1BrownLarge Language Models explained briefly
Andrej Karpathythe one-hour introduction to large language models
IBM Technologythe LLM and RAG explainers
codebasicsthe Gen AI course and the LLM explainer
Tech With TimLearn Ollama in 15 minutes
Amit Thinksthe Ollama installation and custom-model tutorials
KodeKloudRAG explained for beginners
SimplilearnGenerative AI explained in 5 minutes
edureka!the generative AI, LLM and AI ethics explainers

If you are one of these creators and would like a lesson removed or credited differently, write to info@wartens.com.