In the current landscape, generative AI coding tools have become invaluable to developers, but they introduce significant security concerns. The snippets these tools generate are often not secure, and many organizations are hesitant to share their codebases with publicly available models. This talk will guide you through the process of creating a secure coding assistant that is tailored to your specific security needs.

We'll start by examining the security limitations of existing AI coding assistants. You'll gain insights into the challenges these tools face and learn about the importance of fine-tuning models to address these shortcomings.