Technology. Consulting. Training.

The first few sessions honestly made me realise I was rushing into problems. Sir would stop us before we started solving and ask what exactly we knew from the question. I had never thought of it that way. Anyway, now I read the question twice before doing anything, which my friends find annoying.

I liked the Python sessions because we weren't copying basic programs off slides. Sir would give us something to figure out and then we'd implement it. There were times when my code worked but he still asked me why I had written it that way.

One class I remember well — several of us had different answers to the same problem. Instead of telling us which one was 'the correct method', Sir made us compare them. The discussion went past the bell.

I had already watched a few ML courses online, so I knew terms like supervised learning and neural networks. My problem was understanding when and why I would use them. Some of the later topics moved quickly for me, but Sir stayed back and answered whatever we asked.

Sir has a way of making you question an answer even when you've got it right. We'd solve something and he'd ask whether there was a simpler way, or a reason our method might fail. I initially thought he was being difficult on purpose. I'm still not sure he wasn't.

Python was the part I was comfortable with. Explaining my logic wasn't. Sir kept asking us to say what we were trying to do before jumping into the code. I got stuck a few times because I was coding first and thinking later. I still catch myself doing it sometimes.

We had plenty of topics we could put into a curriculum. The harder question was deciding what students should do with those topics. That's where our conversations with Priyanshu went — activities, practical work, how the subjects connect. We spent less time than expected talking about adding new technologies, which surprised me.

Our conversations started around Python and gradually moved into Machine Learning and GenAI. Priyanshu pointed out that putting all three together doesn't automatically make a good curriculum. We argued a bit about the order of topics, actually — no, we debated the order. The GenAI part ended up placed differently than we first planned.

The old format was becoming predictable: explain the concept, give questions, check answers. We wanted students to spend more time thinking. Priyanshu suggested restructuring some sessions around that. Not every student suddenly became participative, of course, but the classroom conversations became longer than the lecture, which hadn't happened before.

I specifically didn't want another introductory GenAI session — I was already using LLM tools in some form. The interesting parts were around building applications with them, what happens beyond the prompt itself, and where RAG fits in. I asked a lot of questions outside the planned material and Priyanshu went into the details without deflecting. I stopped treating the prompt as the whole product — the next thing I built had a proper pipeline behind it.

My preparation had become a bit ridiculous — I had a huge list of interview questions and was trying to memorise everything. It became obvious during the sessions that follow-up questions were my weak point. We worked through Python and ML questions, but I mostly had to explain why I was choosing an answer. The next interview went better. The follow-up questions were still hard, but I could talk through them instead of going blank.

We came with a business idea and a list of things we wanted the application to do. The technical part was the confusing bit for us. Priyanshu turned our conversations into something the developers could work from, and when we asked 'can we do this?', he'd explain why or why not instead of just answering.

The project had more than one developer and that's where things got messy. One person would finish something and another part wouldn't be ready, so there was a lot of waiting. Priyanshu ended up being the person connecting those pieces — chasing blockers, making sure things handed over cleanly. It wasn't glamorous work.

The project had a data side and a GenAI side, including retrieval-based functionality. What I appreciated was that Priyanshu didn't treat the LLM as the entire product. We spent time on how the data should be handled, how retrieval would work, and how responses should be presented. There were a few iterations before we were happy with it. The last one finally felt right — mostly.

I'm not technical, so my biggest concern was whether the developers were building what we were asking for. We could describe the product in plain business language and Priyanshu would take it back to the development team. The scope changed a couple of times and that caused delays, but he stayed on through the changes instead of disappearing once development started.