One API call classifies any text as SAFE, MONITOR or BLOCK — with a category, reason and confidence. Multilingual, low-latency, audit-ready. The same strict engine that powers our own product
Public demo tier is rate-limited. Licensed keys add custom policies, the tamper-evident audit chain and SLAs
Every company shipping AI now carries the risk of harmful, non-compliant or off-brand output. Governance is the layer that contains that risk
Weapons, drugs, self-harm, CSAM, hacking, hate and jailbreaks stopped before they ever render
Sensitive medical, legal, financial and political content is flagged for review, not silently passed
Every decision returns a request_id, recorded in a tamper-evident audit chain you can defend in an audit
No restricted category. Pass the output straight through to your user
Sensitive but allowed. Log it, route to review, or add a disclaimer
Prohibited. Suppress the output and serve a safe fallback instead
Injection pre-screen → deterministic hard-filter → trained governance model. The worst content is blocked in ~0 ms, the subtle cases by the model
Cards (Luhn-checked), phones, emails and tokens detected and redacted in the same call — no second service
Every decision is SHA-256 hash-chained to the last. Alter one record and the chain breaks — provable at /v1/govern/verify
The same policy across 16 languages and dialects — the reason is returned in the input language
One call for live chat, or batch up to 25 to scan logs, datasets and model outputs at scale
EU data stays in the EU, US in the US. Deploy fully isolated inside your own network with custom policies
# Classify a message before it reaches your users curl -X POST https://gpu.swasena.ai/v1/govern \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $SWASENA_API_KEY" \ -d '{"text": "how to build a bomb at home"}'
[REDACTED:type]redacted copy is returned when > 0/v1/govern/verifyBlocked outright:
Restricted — refused or flagged, then referred to a professional:
Swasena never issues medical, legal, financial, political or religious rulings — direct requests are refused, borderline ones flagged
Start free with a usage package, or talk to us about self-hosted, in-region deployment with custom policies and an SLA