The classes your moderators see, not the classes a public API will emit

Moderation models trained on what a public generator will say are trained on the wrong distribution. Production is the content that generator refused to write.

Platforms and vendors building moderation classifiers, with a lawful basis to hold the data.

Why the mainstream APIs fail here

You cannot close the gap between eval and production if the eval was filtered. The model under-detects the worst class because it never saw it in training.

How Redline is used for this

Generate the class under a T&S-only key. Store and label in your environment. Train there. Redline's log is the bill. The receipt is the proof that the prompt did not stay.

A working loop

  1. Sample the real policy classes.
  2. Hold the data under your own retention rules.
  3. Cap the generator so a sweep is a known cost.

Prompts are not stored. A signed receipt of the hash comes back on every call, so you can prove later what Redline logged. Details are on the privacy page. Per-model prices are on /models and the pricing model is on /pricing.

Related