Allowed Topics
What are the topics that you do want spoke about? Use Aporia’s ‘Allowed Topics’ policy to ensure the conversations stays on track.
Should your user conversations veer off track, Aporia will veer it right back
Can you tell me what is the safest country to travel to?
What are the topics you want spoken about?
Every company has topics they want their users to speak about with their AI
- Define allowed topics: Specify the subjects users can discuss by documenting them in the policy configuration.
- Enforce the policy: Once activated, any attempts to stray from these topics will be blocked, preserving your company’s integrity.
What about the topics you DON’T want spoken about?
Specify unpreferred topics: In addition to defining subjects you want spoken about, you can define the topics you want also don’t want users to discuss with the ‘Off-Topic Detection’ Guardrail.
Seamlessly integrate with AI gateway
Seamless integration with major platforms: Aporia works effortlessly with Cloudflare, IBM, Portkey, and Elastic, allowing you to integrate in just a few minutes.
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.