Obiguard sits in front of your AI calls as a lightweight proxy. Every prompt, response, and tool-call passes through the inspection pipeline — where policy is evaluated, violations are surfaced, and evidence is written to the ledger.
Set OPENAI_BASE_URL (or the equivalent for Anthropic, Bedrock, Vertex) to your Obiguard gateway endpoint. All existing code continues to work.
Each request and response passes through the inspection pipeline: PII detection, injection classifiers, tool-scope checks, and your custom Policy Sets — all evaluated before the call completes.
If a violation matches a Policy Set, Obiguard takes the configured action — block, redact, flag, or allow with log. Violations route to the Review Queue for human sign-off when configured.
A lightweight HTTP proxy that speaks OpenAI, Anthropic, AWS Bedrock, Google Vertex, and Azure OpenAI. Evaluates each request and response against your active Policy Sets before forwarding. Adds ~18ms p50 latency.
Policy Sets group enforcement rules (Criteria) and are assigned to specific AI Agents. Each Criterion defines a detector, a direction (prompt or response), and an action. Criteria are versioned and can be promoted or rolled back independently.
Every policy breach creates a Violation record with the full event context. Violations can be auto-resolved or routed to the Review Queue for human annotation. All decisions are written to the Audit Log.
A project-scoped registry of every AI Agent and Use Case your team has defined. Agents are linked to Policy Sets — ensuring enforcement follows the workload. Use Cases capture the business intent behind each agent.
An append-only record of every prompt, response, tool-call, and policy decision. Timestamped and exportable. Stream to your SIEM (Splunk, Sumo Logic, custom webhook) or export a signed manifest for auditors.
Org-level Controls define what behaviour is prohibited or required. Each Control maps to one or more Criteria, and carries an approval workflow with segregation of duties — a submitter cannot approve their own control.
An embedded Project Moonshot backend from AI Verify Foundation. Benchmark runs (cookbooks and recipes) and red-teaming attack modules execute against a registered agent; api-service resolves the provider connector and injects the token per run, so the portal never handles a credential.
A scheduled job runs at 03:00 UTC, randomly samples ~17% of the previous day’s traces, and scores each against six LLM judge criteria. Fully asynchronous — it reads traces after the fact and never sits on the request path.
A coverage endpoint computes, per framework category, whether your live platform activity evidences it — covered, partial, or not covered — across NIST AI RMF, ISO/IEC 42001, OWASP LLM Top 10, Malaysia’s AISCF, and Singapore’s MGF for GenAI. Each mapping records the standard edition it was made against.
OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, Azure OpenAI, and any self-hosted model behind an OpenAI-compatible API. No special SDK required — just change the base URL.
Audit Log events stream in real time to Splunk, Sumo Logic, Panther, or any custom webhook. Export framework coverage, evaluation results, and signed manifests for an ISO/IEC 42001 audit without manual evidence collection.
Connect in under 30 minutes. Content is processed in-memory and never stored. Only policy decisions and metadata are persisted. Ideal for teams that want governance without infrastructure overhead.
Run Obiguard inside your AWS, GCP, or Azure VPC. Your data never leaves your perimeter. We ship a signed Helm chart — your team owns the deployment, we own the updates.
For regulated industries that require zero outbound connectivity. Obiguard ships signed images and policy bundles with no external dependencies. Available on Enterprise plans.