Explore prompt caching

- explore what it is: https://ai.google.dev/gemini-api/docs/caching and https://developers.openai.com/api/docs/guides/prompt-caching This will require prompt re-writing where we may have to move all of the static context at the start. IMPORTANT: Start with ONE of the prompt ONLY. End goal expectation: can it make our responses faster + reduce cost + while preserving response quality (MOST IMPORTANT) - End goal expectations need to be verifiable so make sure to share a sheet containing: user_message, old_ai_response, new_ai_response, chat_history (3-5 msgs prior to user message), response_time (time taken for new_ai_response to generate)