Demo library GA 4.13.4
← All demos

Nordic guardrails: Azure PII and Content Safety on the Gravitee AI gateway

Azure AI Language and Content Safety can guard a Nordic-language chatbot from the gateway today, masking personal data and refusing threats and prompt injection before the model is called

Pre-release build Internal only

Made for Posten Bring

Say while it plays

  1. Gravitee's native guardrail was masking organisation names as personal data and letting non-English threats and prompt injections straight through, so this chains two Azure services, Content Safety and Language, onto the LLM proxy as a stopgap ahead of native non-English support.
  2. Two Groovy steps do the work: one shapes each turn into the callouts for PII detection and harm and injection scoring, the second decides whether to mask or block, and a blocked call returns a 403 with the downstream model never called.
  3. Testing blocked 35 of 39 harmful Nordic prompts with no false positives, and the setup fails closed, so if Azure is unreachable the prompt never reaches the model at all.

Don't claim

  • Don't claim reliable Finnish coverage: the recording says Finnish is where it falls short, because Azure itself says it wasn't really trained on that language.
  • Don't claim deep multi-turn prompt injection is solved: the recording says hiding an injection deep within a multi-turn conversation isn't perfect either.
  • Don't present this as native Gravitee guardrail functionality: the recording calls it a workaround built from Azure callouts to get live before native non-English support lands in 4.14.

Chapters

  • Problem overview & temporary workaround
  • Azure resources and Policy Studio configuration
  • Groovy scripts linking gateway to Azure services
  • Demo traffic, detection results, and logging
  • Performance metrics, limitations, and next steps

Run it live

Open the live demo in the runbook

URLs, whether it is up right now, and the gotchas.

Related demos