Admin guideMembers and roles, sign-in, your own runners, runtime health, transcripts and runs.

Admin guide · AI

AI transcripts

Every call a model made on your organisation's behalf: what went to it, what came back, and what the guardrails found. A finding is a prompt for a person; the verdict is yours.

WhereSettings › Insights › AI transcripts
WhoAn admin, or anyone whose role may configure AI
PlansEvery plan; how long they are kept follows your plan
The AI transcripts page: a filter by conversation, Needs review, how long transcripts are kept, and a table of model exchanges with When, Verdict, Findings, Brief, Model and Turn
AI transcripts: each model exchange with its verdict, findings, the request it served, the model and the turn. Click to open full size.

Read the table

ColumnWhat it says
WhenThe time of the call
VerdictClean, or Needs review when a guardrail found something
FindingsWhat was found, such as an email address in the text
BriefThe request the call served
ModelThe model that answered
TurnWhich turn of the conversation

Review an exchange

  1. Tick Needs review to see only the exchanges with findings, or filter by a conversation's id.
  2. Open one: Data check, Sent to the model and Received from the model, word for word.
  3. A verdict - Mark compliant or Mark violation, with what was found or why it is fine - is recorded by an operator with the security scope.

How long they are kept

The page says how long transcripts are kept on your plan. Set a shorter time under Keep for (days) and press Save. A finding nobody reviewed stays until someone does.

Last updated October 29, 2026