Congratulations on making it to the end of the course. You've covered a lot. From the detailed foundations of reinforcement learning with GRPO, to the art and science of creating reward functions that steer LLMs to good performance on complex tasks. Crafting reward functions for RFT is very flexible. And there is a lot of scope to insert your own domain knowledge since you build the functions from scratch. We've worked with lots of customers at Predibase We're coming up with interesting and creative RFT solutions for their business problems. Including the quiz taking reward function for summarization that you saw earlier in the course. If you are interested in going deeper, there are more RFT learning resources on the Predibase website. And because this technique is still in its infancy, we'd love to hear from you about any use cases you explore. We hope you enjoy the course and we can't wait to see what you build.