Prompt capture

Off by default, and the setting that deserves the most thought before you turn it on.
What it does
Stores the actual content of conversations — what developers typed and what the model
replied — so you can read them later on the Conversations screen.
Without it you still get everything else: who, when, which tool, which model, what the
policy decided, what the detectors found. What you do not get is the text.
Before you turn it on
Tell your team. Not because the law necessarily requires a specific notice in your
jurisdiction, but because discovering afterwards that their prompts were being stored is
the fastest way to lose your developers' cooperation — and a governance programme that
your engineers are working around is worse than none.
What protects the content
Redaction happens before storage. Secrets found by the detectors are replaced with a
marker naming the kind, so the stored transcript contains 
[REDACTED:aws_access_key_id]
rather than the key. In the console these render as amber shield badges.
It follows your retention setting and is purged with everything else.
Sentilai support cannot read it. Support can see that a request happened and what
the policy decided. The content is yours.
Turning it on
Policy → Prompt capture. Conversations then start appearing on the Conversations
screen. Until then that screen shows an explicit "Prompt capture is off" state with a link
back to Policy, rather than an empty list that looks like a bug.