Ask HN: How do you iterate on and manage prompts in production?
I'm curious about how people handle managing and iterating on their prompts, especially for production-facing prompts that many users depend on.
- Where do you store your prompts?
- Do you use version control?
- How do you test prompts after editing?
- Where do you store your test sets?
- Do you evaluate results? If so, how?
- Are you fine-tuning models like GPT-3.5 for better/cheaper results?
- Where do you store your prompts? - Do you use version control? - How do you test prompts after editing? - Where do you store your test sets? - Do you evaluate results? If so, how? - Are you fine-tuning models like GPT-3.5 for better/cheaper results?