Generative AI is powered by Large Language Models (LLMs) which may be proprietary LLMs or open-source LLMs. Fine-tuning of LLMs refers to the practice of taking a pre-trained model (which is typically trained on a massive and diverse dataset) and subsequently training it further on a more specific or narrower dataset. The aim of this additional training phase is to adapt the model to particular tasks or domains, enhancing its performance on those tasks or domains without requiring it to learn everything from scratch. This talk is focused on defining the building blocks and processes that are necessary to create fine-tuned LLMs for CRM systems. The value proposition is a pragmatic GenAI solution that can help in increasing the productivity by automating various manual steps in CRM transcript analysis. Such a GenAI solution could serve as an invaluable copilot for a CRM manager.