# Concepts

The ideas behind Latent: what it scores, what counts as a failure, how it learns your traffic and what it keeps.

- [Scored answers](https://runlatent.ai/docs/concepts/scored-answer.md): What 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 standards](https://runlatent.ai/docs/concepts/failure-standards.md): The 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.
- [Calibration](https://runlatent.ai/docs/concepts/calibration.md): How 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 retention](https://runlatent.ai/docs/concepts/data.md): What 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 answers](https://runlatent.ai/docs/concepts/streaming.md): How 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 answer](https://runlatent.ai/docs/concepts/act-on-a-flagged-answer.md): What 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.