Why it matters

Content filter shapes safety. Foundation for public apps.

Advertisement

The architecture

Provider moderation API.

Open classifier (Llama Guard).

Combine + threshold.

Content filter stackProvider APIOpenAI / AzureOpen classifierLlama GuardCombineblock or allowLayered filters catch different categories; watch false-positive rates
Content filter.
Advertisement

How it works end to end

OpenAI Moderation, Azure Content Safety.

Llama Guard for open self-host.

Category-based blocking.

Waivers for legit cases.