Don't teach something until it's been around for five years.

GPT-3 turns five this year. Long enough for the hype to settle and the real failure modes to surface. Which is exactly when we built this workshop.

Amit Kapoor

My rule: don't teach something until it's been around for 5 years.

That's usually how long it takes for the hype to settle down and the real strength, limitation and failure modes to show up.

GPT-3 came out in June 2020. LLMs are five years old. We finally know a little more now about what actually works, what breaks, and what people keep getting wrong.

So Bargava Subramanian, Anand Chitipothu and I have built a workshop around that gap. A workshop focussed on fundamentals. What happens after the first API call? How do LLM products actually evolve into reliable systems?

We will build one product together, layer by layer: Search → Prompt → Schema → Context → State → Memory → Tools → Evals

Each layer fixes a real failure. Nothing is added because it's fashionable.

One day. One product. Eight layers.

13 June · Bengaluru · ₹4,999 · 30 seats