Obiguard's inspection pipeline sits in the critical path between your application and the model. Every token in and every token out is evaluated against the Criteria in your active Policy Sets before the call completes.
Every user prompt and system message is scanned for injection attempts, policy violations, PII, and off-scope content before the request reaches the model.
Model completions are inspected before delivery. Obiguard can redact, block, or flag content — with the original preserved in the audit ledger.
Agent tool invocations are validated against your registered allow-list. Calls to out-of-scope tools are blocked — logged with full context.
Jailbreak/injection, PII, NSFW, toxicity, gibberish, profanity, ban list, competitor mentions, and format guards.
Synchronous, in-path inspection — not a background log processor.
Email, phone, IP, location, person, URL — plus SSN, credit card, passport, IBAN, bank and driver licence numbers.
Detector and policy activity feeds coverage against NIST AI RMF, ISO/IEC 42001, OWASP LLM Top 10, Malaysia’s AISCF, and Singapore’s MGF for GenAI.
