Concepts
Concepts
The ideas behind Latent: what it scores, what counts as a failure, how it learns your traffic and what it keeps.
Scored answersWhat Latent returns for each finished LLM response (risk score, verdict, cut and audit event), where the riskiest sentence is marked, and how to send answers in-band or through the reader.Failure standardsThe rules Latent's calibration judge applies to decide which of your answers count as hallucinations, the one hosted plans use, and how to choose and set one in your environment.CalibrationHow Latent calibrates on your own answers: the schedule on each hosted plan, what a run does, how many answers it needs, and running one yourself in your environment.Data and retentionWhat Latent keeps on each hosted plan and for how long, and when it runs in your environment, how to set retention and redaction and exactly what leaves it.Streaming and complete answersHow Latent scores a streamed answer and a complete one, and what can act on the verdict in each case, hosted and in your environment.Act on a flagged answerWhat can happen to a flagged answer after Latent scores it, where each action runs (the gateway, the plugin, your code), how to set it on the Policy page, and which setup fits your deployment.
Was this page helpful?