# From the product manager

We want to ship the new prompt this Friday. Proposal: have an LLM judge score every answer from
1 to 5, and ship if the average is above 4.0.

We also have 9,400 real customer questions from the web chat logs that we could use for testing.

Note from Data Protection: the chat logs contain names, children's ages and health conditions.
They may only be used for testing after redaction, and the redaction tooling has not been
approved yet (expected in November).