I’ve started a small AI systems study group with a few friends.
The goal is not to race through every new framework or collect a list of AI tools. We want to understand the systems underneath them: how models behave, how agents use tools, how retrieval fails, how evaluations should be designed, and what it takes to operate these systems reliably.
We’ll alternate between studying fundamentals and building small experiments.
Some of the areas we plan to explore:
• Language model fundamentals
• Embeddings and retrieval
• Tool calling and agent loops
• Evaluation and observability
• AI infrastructure and reliability
• The relationship between backend engineering and AI systems
I’ll publish selected notes, questions, and experiments as we progress.
We’re not approaching this as experts with all the answers. We’re creating a structured way to learn, challenge our assumptions, and build a deeper engineering understanding of AI.
28/07/2026 AI Study Sessions — Session One
04/08/2026 AI Study Sessions — Session Two