If you are running an AI app in production, you want to give your users the latest and greatest features, while doing everything possible to ensure their experience is smooth and bug free. Decoupling deployments from AI configuration changes is one approach to reduce risk.` LaunchDarkly's new AI configs can help achieve this by allowing you to change your model or prompt at runtime without needing to deploy any new code, thereby granting developers a ton of flexibility to roll out changes quickly and smoothly. The tutorial covers how to use AI configs to upgrade the OpenAI model version in a Python FastAPI application, including setting up a developer environment, creating an AI config, and progressively upgrading to a newer model while minimizing risks to users. Additionally, it highlights potential future upgrades such as tracking output satisfaction rate, prompt improvements, and advanced targeting.