Related products and practices, with creator experiences across different uses.
With use and recommendations from
Technique
Scoring subjective agent outputs like whether the right information was extracted into an issue's title and description
"It's LLM as a judge. We build out this dataset over time, then we just have a scoring type of LLM that's like: did this extract the right information? This is what it should be, pretty much."
Technique
Automatically grading AI agent conversations against quality rubrics and auto-fixing below-threshold interactions without founder involvement
"Every day I have an automation that looks at these chats and grades them on a rubric. If anything is bad or below this score, I want you to kick off a child session and fix it. It is shocking to me the number of small UX details that have been picked up by ..."
Products are related to this topic through catalog tags. Quotes describe the creator’s stated use; they are not necessarily recommendations for this topic.
Creator counts cover all uses and all dates. Each person counts once per product family. Paid promotions and passing mentions are excluded. Items are ordered by creator count, then name.
