Custom Policies
While we offer out-of-the-box policies, we also offer the option to create custom policies in minutes with our custom policy generator.
No prompt engineering needed. Create custom policies in minutes
Step 1: Choose your detected behavior
Define the behavior to detect: Specify the behavior you want to monitor by writing it in the ‘Detected Behavior’ box, including the special tokens needed to identify questions, context, or answers for evaluation.
Step 2: Add in your context and choose your behavior
- Determine policy classification: Decide if the policy should treat the detected behavior as a violation or a legitimate response.
- Specify the context: Indicate any relevant context for how the information should be interpreted, if applicable.
Step 3: Test the policy, & activate
- Test the policy in real-time: Use our sandbox to evaluate the policy’s effectiveness and ensure it behaves as expected.
- Activate and monitor: Once satisfied, activate the policy and track its performance using the Session Explorer.
Less than 5 minutes to get started
A few minutes of configuration, for an endless level of security and reliability for your AI Agent.
Start For FreeState-of-the-art accuracy:
Aporia's multiSLM Detection Engine
Aporia uses multiple SLM engines instead of a single LLM to achieve exceptional speed and accuracy. This approach ensures that your app’s user experience remains smooth and unaffected.
Learn more about our multiSLM Detection Engine.
Up to 300ms
guardrail latency93.7%
average precision94.2%
average recallEnterprise-grade security standards
Designed to help enterprises of any size deploy safe and trustworthy AI apps.
Private
Cloud or custom deployment so your data never leaves.
Secure
Battle-tested by Red Teaming to ensure highest standards are met.
Compliant
Aporia is HIPAA, SOC 2, Pentest and GDPR certified.
