Product AI Development course

Before the first course, AI-Driven Development, I had almost no experience working with agents. The course gave me an understanding of what kinds of agents there are, which ones to use and what tasks you can solve with them. And something I didn’t expect at all: you can build products on all of this, and do it yourself, almost single-handedly.

The second course, Product AI Development, gave me more confidence: you can build fairly robust production products on generative AI, and it’s closer and simpler than it seems at first glance. I had experience building various systems, but I hadn’t built systems like these before – now I do. The topics are comprehensive, the homework is substantial, I had to dig into it, and I liked that. Most of all I liked the review of my AI work sessions: seeing from the outside, with an assessment, how I use AI is a very good tool, and I’ll keep using it.

I liked the course, there’s not much to criticize. It turned out deep in its materials: it’s hard to study everything to the end, but it covers the top-level understanding – what to try and where to go deeper. It’s all really cool: during the course I already managed to ship one chain to production.

What I value most is the format of working through questions and problems. You can study the theory afterwards in any convenient form – a recording, a summary, text. But you won’t get a discussion of real questions just anywhere: for that you need to find a group of people or a meetup.

I take courses like this not to level up 100% as an engineer, but to broaden my perspective. Technology is developing at tremendous speed, you can’t keep up with everything, and when you come and everything has already been structured for you, that’s worth a lot. So I really enjoyed it. I didn’t understand everything 100%, but you can always go back to the materials and quickly figure out what to develop.

I really liked how Sergey ran the sessions: he went beyond the program, compared things with Google and other solutions, and after that a real interest in working with the technologies woke up. The course met my expectations 100%. The main idea I took away: thanks to AI, the very nature of business is changing, nobody relies on long-term versions anymore, so you need to build your own abstract solutions that cover as many providers as possible.

I started to understand much better how AI systems work under the hood: for me it’s no longer a black box like it used to be. That understanding was super useful.

I’m completely happy with both the direction of the course and its content. There wasn’t a single weak homework that makes you think “what’s the point of all this” – everything went into my piggy bank. I especially liked the depth I saw at the final stages.

I liked that you can do part of a task at an intermediate level – a good compromise: you try, make mistakes a few times, correct yourself and see it through to the end. After all, we came here for practical experience – not only for hard skills, but also to strengthen our soft skills and practice them.

The course covers all the AI topics that matter right now. When you study on your own, it’s hard to focus on what really matters. Here, the theory is laid out step by step and in real depth. I liked that you don’t have to look for other sources – everything is in one place. The course project is a great sandbox for trying out your skills.

Doing the homework was a pleasure. You could see how carefully everything had been thought through and how much effort had gone into it. The homework always came with clear instructions, and it was clear what result was expected. The amount of work and material is huge: it felt like the team had packed a year-long AI course into 2 months.

I think it’s a good foundation for getting certified later on. The course is definitely worth the money – and more. I’d take it again, with a different course project.