Generative AI & Vibe Coding
Build and deploy real software with AI — and understand what you shipped.
A ten-week live course in building software with AI assistance, for people who are not programmers. Prompt engineering that produces reliable structured output, then websites, web apps and automations built and deployed for real — including the security and review habits that separate working software from a demo that leaks its API keys.
- Duration
- 2.5 months
- Live teaching
- ~33 hours
- Fee
- ₹9,999
- Format
- Live online
Who this is for
Non-programmers, founders, marketers and operations people who want to build the tool instead of waiting for one.
Prerequisites
- None beyond everyday computer use
- Willingness to read code you did not write
Who it is not for
Experienced developers — you will find modules 1 through 3 slow. Look at AI Engineering.
Compare all five courses →Outcomes
What you will be able to do
Written as capabilities rather than topics, because a topic list tells you what was said in the room and not what you can do afterwards.
- Write prompts that produce reliable, structured, usable output
- Build and deploy a website and a working web application
- Read and reason about code you did not write yourself
- Automate a real business process with error handling
- Handle secrets, environments and version control safely
Curriculum
7 modules, ~33 live hours
Every module states the hours it takes and what you can do at the end of it.
01The model landscape
3.5 hrs
The model landscape
- ChatGPT, Claude and Gemini: real differences, not marketing ones
- Context windows, and why long conversations degrade
- What a task costs, in tokens and in rupees
- Choosing a model per job rather than per habit
After this module: Pick the right model for a task and know roughly what it will cost.
02Prompt engineering
5 hrs
Prompt engineering
- Structure, role, constraints and examples
- Few-shot and chain-of-thought, and when each is wasted effort
- Structured output: JSON that parses every time
- Iterating on a prompt like code, with a test set
After this module: Get reliable, parseable output instead of well-written prose you cannot use.
03Vibe coding I — from spec to running page
5 hrs
Vibe coding I — from spec to running page
- Writing a spec an AI can build from
- Scaffold, run, read, iterate
- Reading code you did not write, and the questions to ask it
- When to start over instead of patching
After this module: Ship a working landing page and be able to explain every file in it.
04Vibe coding II — a real web application
6 hrs
Vibe coding II — a real web application
- Data models and a real database
- Authentication and who can see what
- Forms, validation and error states
- Deploying to a live URL
After this module: A deployed application with a URL you can send to someone.
05App development with AI
5 hrs
App development with AI
- Progressive web apps and mobile-first layout
- Calling third-party APIs and handling their failures
- Storage, offline behaviour and installability
- Testing on a real phone, not a resized browser
After this module: An installable app that talks to a real API.
06Automation, workflows and agents
5 hrs
Automation, workflows and agents
- n8n: triggers, nodes, branching, error paths
- Webhooks and scheduled jobs
- Giving a model tools, and bounding what it may do
- Human-in-the-loop checkpoints for anything irreversible
After this module: Automate one repetitive business process end to end, with a failure alert.
07Shipping without regret
3.5 hrs
Shipping without regret
- Git as an undo button you can explain
- Environments, secrets and the API key that must never reach GitHub
- The security mistakes AI-generated code makes most often
- What actually breaks in production, and how you find out
After this module: Deploy without leaking a credential or losing a week of work.
Projects
What you will build
Each one exists to prove something specific to someone who is deciding whether to hire you.
Deployed portfolio site
You can ship something public.
A CRUD web app with auth
You can build software with state and users.
One live automation
You can remove a recurring task from your week.
Tools you will actually use
How it runs
What a week actually looks like
Live, not recorded
Sessions are taught live so you can interrupt. Recordings are shared afterwards for anyone who misses one.
Small batches
Small enough that everyone gets looked at. If a batch gets large, it splits rather than scales.
Doubt support
A dedicated channel between sessions, and time set aside in each class for questions from the last one.
Cadence
Two to three live sessions a week, evenings and weekends on Indian Standard Time, so it fits around a job.
The certificate
A certificate of completion, issued by NKable, confirming you finished the course and its projects. It certifies completion — not proficiency — and it is not a university qualification. It is not affiliated with, accredited by, or issued on behalf of any university.
What is not included
- A computer-science education — you will build software, not become a software engineer
- App-store publishing for iOS or Android
- Paid hosting, domains or AI subscriptions beyond the free tiers used in class
- Job placement or freelance client guarantees
Career support, itemised
So “career guidance” cannot be read as a job promise, here is exactly what it means.
- Portfolio and deployed-project review
- Guidance on positioning this skill inside a non-technical role
- Freelance scoping and pricing for small build work
Full course fee
₹9,999
2.5 months · ~33 live hours · no separate material or exam fees
Enrol in this courseAsk a question firstFees are payable after a short call, not from this page. Refund policy · Enrolment terms
Who teaches this
Nishi Kant Chandra
Based between New Delhi, India and Moscow, Russia
MBA in Business Analytics from O.P. Jindal Global University (O grade), and an M.Sc. in Business Analytics & Big Data Systems from HSE University, Moscow. Google-certified in Data Analytics, with advanced prompt engineering from Vanderbilt. Two and a half years supporting a SaaS platform’s enterprise clients, and the person who built and maintains every tool on this site.
See the full background and the work →Generative AI & Vibe Coding — questions people ask
What is vibe coding, exactly?
Building software by describing what you want to an AI assistant and iterating on what it produces, rather than writing every line yourself. It is genuinely effective and genuinely dangerous in equal measure, which is why the last module is about the security and review habits that keep it from producing something that leaks its own API keys.
I have never written code. Can I really do this?
Yes, and that is who the course is designed for. What you do need is a willingness to read code you did not write and ask it questions. People who refuse to look at the output and only paste error messages back struggle, whatever their background.
Will I be a software engineer at the end?
No, and the course says so on the page. You will be able to build and deploy working software and understand what you shipped. A computer-science education is a different thing and takes years.
Which AI coding tool do you teach?
The patterns first, then a tool. Tools in this category change every few months, and students who learned one tool rather than the underlying approach are stranded when it does. Claude and an AI coding editor are what we use in class.
What does the automation module cover?
n8n workflows with triggers, branching and error paths, webhooks, scheduled jobs, and giving a model tools with explicit bounds. Anything irreversible gets a human approval step, which is the difference between an automation and an incident.
Is this the same as the AI Engineering course?
No. This one is about building software with AI as your assistant. AI Engineering is about building the AI systems themselves — retrieval, evaluation, agents, production deployment — and it assumes you can already write Python.
What does the Generative AI & Vibe Coding course cost?
₹9,999 for the full 2.5 months, covering roughly 33 hours of live teaching plus the projects. There are no separate material or examination fees. Refund terms are on the refund policy page.
How long is the course and how much live teaching is there?
2.5 months, with about 33 hours of live sessions across 7 modules. Sessions are live and online, not recorded lectures you watch alone.
What do I need to know before starting?
None beyond everyday computer use. Willingness to read code you did not write.
Is there a certificate?
Yes — a certificate of completion issued by NKable, confirming you finished the course and its projects. It certifies completion, not proficiency, and it is not a university qualification: it is not affiliated with, accredited by or issued on behalf of any university.
What is not included?
A computer-science education — you will build software, not become a software engineer; App-store publishing for iOS or Android; Paid hosting, domains or AI subscriptions beyond the free tiers used in class; Job placement or freelance client guarantees. Saying this plainly is deliberate — every course page lists what is included, and almost none say what is not.
Enrol
Join the Generative AI & Vibe Coding cohort
Message me and tell me what you want to be able to do afterwards. If this course is not the right one for that, I will say so and point you at the one that is.
+91 99991 03353
Opens the chat with your message already written. Usually answered the same day.
[email protected]
Opens your mail app with the subject filled in. Better for anything long.
Nothing is charged from this page. You get a reply with the next batch date, the schedule and the fee, and payment happens separately after a conversation.