This talk explores our work at Mistral training Large Language Models to enhance programmer productivity. We will discuss key applications such as in-IDE code completion, canvas and agentic code-assistant, demonstrating how LLMs can automate tasks and allow developers to focus on high-level design. We will provide insight into the pre-training and fine-tuning methodologies of our latest models. Attendees will get a clear understanding of how LLMs can be applied into their workflows and of common use cases of LLMs for code.