The exploration of leveraging Large Language Models (LLMs) to contribute to the generation of Software Development Kits (SDKs) at liblab has been enlightening but challenging. The experiment aimed to enhance internal development processes and maintain a competitive edge in the rapidly evolving tech landscape. Despite achieving partial success in generating SDK components, the integration proved time-consuming due to limitations such as non-determinism and hallucinations, input and output limitations, response time and cost implications, state and memory constraints, and security concerns. The journey has underscored the importance of clarity, precision, and simplification in interactions with LLMs and highlights the current impracticality of relying on AI for SDK generation due to these challenges.