Hi @ryan8,
In your case your probably looking more in the direction of Fine-tuning, https://platform.openai.com/docs/guides/fine-tuning/fine-tuning this would be the option to influence the output generated by Davinci etc., but is a bit more complicated.
regarding documentation: https://platform.openai.com/docs/guides/chat/instructing-chat-models (Refer to the section “Instructing chat models” - it is a bit thin but gives you the overview on how to give instructions.
Here are some examples on how this can work out: