In my review of the AZ-900 course, I complained that it was overly theoretical and that more exercises would have been beneficial for reinforcing key concepts. The more practical nature of AI-102 confirms the correctness of my intuition.

I supplemented Microsoft’s course material with https://www.youtube.com/watch?v=scJ4mobwjBQ, which

I was able to skip most of the Azure Monitor AI services module because much of it is already covered in the AZ-900, which I recently completed.

There is an overlap between this the AI-102, DeepLearning.AI’s and HuggingFace’s LLM course.

Normally, I would think twice about this kind of overlap because I would question if I am really spending my time wisely, but because

I only feel that this is welcome actually becomes it helps me to solidify the fundamental

Most interesting

I liked how much focus there was on safety and responsbility in this course. For example, the course introduces Azure Content Foundry Safety and its custom safety solutions feature. In addition to common categories such as hate, sexual, self-harm and violence, since we all have different sensibilities and so might our different audiences.

These are particularly interesting today with the vibe shift that is taking place in the states but that’s also gaining some traction in Europe. Values are being turned upside down and some of what was considered hate yesterday isn’t today.