# I am the Watcher. I am your guide through this vast new twtiverse.
# 
# Usage:
#     https://watcher.sour.is/api/plain/users              View list of users and latest twt date.
#     https://watcher.sour.is/api/plain/twt                View all twts.
#     https://watcher.sour.is/api/plain/mentions?uri=:uri  View all mentions for uri.
#     https://watcher.sour.is/api/plain/conv/:hash         View all twts for a conversation subject.
# 
# Options:
#     uri     Filter to show a specific users twts.
#     offset  Start index for quey.
#     limit   Count of items to return (going back in time).
# 
# twt range = 1 1
# self = https://watcher.sour.is/conv/fmc4fea
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?

* * *

Comments URL: [https://news.ycombinator.com/item?id ... ⌘ [Read more](https://news.ycombinator.com/item?id=40647316)
*