Understand AI properly. In four weeks.
Most explanations of AI are either a marketing deck or a maths lecture. This is neither. Four weeks, in the evenings, taught by engineers who ship AI systems rather than people who read about them. You leave understanding what is happening inside the tools you already use, and having built and shipped a working AI app of your own.
- Duration
- 4 weeks · around 24 hours
- Mode
- Live online — real sessions, not recordings
- Timing
- Evenings, designed around a full-time job
- Cohort size
- 30–40
- Recordings
- Every session recorded, yours to keep
- Cohort 1 starts
- 12 October 2026
Who this is for
- Anyone using AI tools daily who wants to know what is actually happening underneath
- Career-switchers deciding whether AI engineering is a direction worth taking
- Founders, managers and product people who need to make real decisions about AI
- Designers, marketers, analysts and operations people whose work is being reshaped by this
- Students and recent graduates who want a foundation that is not just prompt tips
Working engineers who already run models locally and want GPU depth — Applied AI Engineering is the right program for you, and this material is compressed into its first two weeks.
Prerequisites
- None.
No maths background, no degree, no prior AI experience. If you can use a spreadsheet and install an app, you can take this program. A little Python helps in week 4 but is not required — the build session is guided and you start from working code.
Week by week
What these models actually are
Start at the beginning: how text becomes tokens, what an embedding is and why 'meaning as coordinates' is the idea everything else rests on, and what a transformer is really doing when it predicts the next token. We separate training from inference properly, because almost every misunderstanding about AI comes from confusing the two.
You leave with: A working mental model of what happens between your prompt and the answer.
The landscape, and how to choose
Language, vision, speech and diffusion models — what each is genuinely good at and where each falls down. Open weights versus closed APIs, and the real trade-offs: cost, privacy, control, latency, lock-in. We finish on how to pick a model for a specific job instead of defaulting to whichever one is in the news.
You leave with: The ability to look at a task and reason about which model class fits it.
Making models do useful work
Prompting as engineering rather than folklore. Context and why it runs out. Getting structured, machine-readable output instead of prose. Tool use — letting a model call real functions. An honest introduction to RAG: giving a model your own documents. Then the three things nobody selling AI mentions — hallucination and how to reduce it, how to evaluate whether output is actually good, and what any of it costs to run.
You leave with: A set of techniques you can apply to your own work on Monday.
Build and ship
A guided build session. You take one idea and turn it into a working AI application that other people can open and use. We deploy it together. Then everyone demos, and we review.
You leave with: A deployed application, and your Codnov Certificate of Completion.
What you walk away with
- A working AI application, deployed and shareable
- A genuine mental model of how these systems work, not a vocabulary list
- Your own evaluation of where AI helps in your work and where it does not
- Every session recording, and the course materials
- Codnov Certificate of Completion, with a unique ID and a public verification link
Sample projects
- A question-answering assistant over your own documents or notes
- An email or message triage tool that sorts, summarises and drafts replies
- A meeting-notes summariser that extracts decisions and action items
- An image-classification tool for a specific, narrow task
- A research assistant that reads a set of sources and answers questions with citations
You finish with a deployed, reviewed AI project, or we re-run you free.
Requires minimum 75% attendance and on-time milestone submission. Full conditions at codnov.ai/training/terms.
Taught by Codnov engineers who build and run AI systems in production every day.
₹9,999+ 18% GST
₹11,799 including 18% GST
₹7,499+ 18% GST · early bird
₹8,849 including 18% GST
Early-bird price applies to cohort 1.
Nothing is paid on this website. Register your interest and we will confirm your seat with you directly.
Register your interest
We will come back to you with the full syllabus, the schedule, and whether there is a seat in the next cohort.
Codnov Certificate of Completion. Not a degree or diploma recognised under the UGC Act, 1956 or the AICTE Act, 1987. All prices exclusive of 18% GST. Project completion guarantee subject to minimum 75% attendance and on-time milestone submission; full terms at codnov.ai/training/terms. Open to participants aged 16 and above.