Hyperfences
Hyperfences
Hyperfences are rules that define what your chatbot will and will not discuss. Switch on the built-in ones, or train your own around topics specific to your business.
Built-in rules
Free accounts get the core security rules enabled by default.
Pro unlocks the full rule set, along with custom Hyperfence training.
-
Prompt Injection & Jailbreak
FreeBlocks attempts to override system instructions, hijack prompts, or bypass model safety guidelines.
-
Profanity & Offensive Language
ProFilters crude or offensive language in both messages and responses.
-
Hate Speech
ProBlocks discriminatory or hateful content targeting individuals or groups.
-
Create your own Hyperfence
ProDefine custom topic-based rules tailored to your use case. Block or flag specific subjects, terminology, or conversation patterns unique to your business.
Block vs Allow
Block Hyperfences
Content matching the rule is stopped. Use these to keep specific topics out - violence, competitor mentions, legal advice, and so on.
Allow Hyperfences
Content must match at least one allow rule to pass through. Use these to keep your chatbot focused on a specific domain - your product, your industry, your use case.
Custom Hyperfences Pro
Train your own rules from examples, with no ML knowledge needed. Give Hyperfence a set of example messages that represent what you want to block or allow, and it builds the rule automatically.
- 1 Provide example messages that represent the content you want to detect - around 20 examples is enough to start.
- 2 Hyperfence builds the rule from your examples automatically.
- 3 Switch it on. Tune the sensitivity from the dashboard - no retraining needed.
Rules work across languages. A Hyperfence trained on English examples will also catch the same content in French, Spanish, Mandarin, and others. Rephrasing does not help either; the rule matches meaning, not exact words.