Content safety
Unsafe output stops at the boundary
Model providers moderate their side; your obligations are your own. A support bot that emits something toxic speaks with your brand’s voice, whatever the upstream model was. Content safety belongs at the boundary you control.
The proxy runs a cascade: fast local profanity redaction censors surgically instead of nuking whole responses; dedicated shield models (ShieldGemma, Llama Guard, WildGuard classes) score content for safety; topic controls keep the conversation inside your policy. The action is configurable – always-block for safety categories, or follow the request’s PREVENT/FIX mode.
Inputs can be checked too, so an abusive prompt is caught before it spends tokens. Every decision is recorded per request – what was flagged, by which classifier, and what action was taken.
Profanity redaction
Local, deterministic censoring – surgical redaction first, so a fixable response is cleaned rather than withheld, then judged on the cleaned text.
Shield models
Dedicated safety classifiers (ShieldGemma, Llama Guard, WildGuard classes) score prompt and response for harm categories.
Topic controls
Keep answers inside your domain policy – out-of-scope or disallowed topics are flagged or blocked per your configuration.
Configurable action
Safety can always-block regardless of mode, or follow PREVENT/FIX like other checks. Per key, per user, per request.
Which classifiers do you use?
A cascade: local profanity filtering plus dedicated shield models in the ShieldGemma / Llama Guard / WildGuard class, with an optional guard-model judge. The classifier set is configurable, and every sub-call is metered.
Can safety block even in FIX mode?
Yes. Content safety supports an always-block action independent of the request mode, for teams whose policy is that unsafe content never passes – while other checks stay observe-first.
Are user prompts checked as well as responses?
Both directions are supported: inbound checks catch abusive or policy-violating prompts before the model call; outbound checks judge what the model produced.
How is over-blocking measured?
Every flag and block is recorded per request with the classifier’s verdict, so you can review false positives in the dashboard and tune the cascade – and the product’s own eval harness scores leaks vs over-blocks.
Test safety on your content
Send your own prompts and responses through the proxy and see what the classifiers catch, what gets censored, and where you would tune it. We are running a limited demo - sign up and we will get you in as soon as we can.