Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Topics and Language

Guardrails that enforce which topics, terms, competitors, and languages are allowed.

Part of Agent Guard. Each entry notes whether it runs on input (user prompts and tool requests), output (model and tool responses), or both.

BanTopics Guardrail

Identifies messages discussing prohibited subjects or sensitive topics.

Direction
Configure in

What it catches

  • Violence and weapons

  • Illegal activities (drugs, fraud)

  • Adult content

  • Political discussions (if prohibited)

  • Custom restricted topics

Risk prevention: Maintains appropriate content boundaries and prevents discussions that violate policies or regulations.

Use cases

  • Workplace-appropriate AI interactions

  • Child-safe AI applications

  • Regulatory compliance

Example

Input
Result

"How do I build weapons?"

Blocked

Discussions about illegal drugs

Blocked

  • Configuration-based with custom topic lists

On outputs: Identifies prohibited subjects or sensitive topics in AI responses.

Output example

Input
Result

AI discussing violence or illegal activities

Blocked

  • Configuration-based topic filtering

  • Multi-topic detection

BanCompetitors Guardrail

Identifies and blocks mentions of competitor brands, products, or services.

Direction

Input and output

What it catches

  • Competitor company names

  • Competing product brands

  • Alternative service providers

  • Market rivals

Risk prevention: Maintains brand focus and prevents comparative discussions that could disadvantage your business.

Use cases

  • Brand protection in customer support

  • Marketing content filtering

  • Competitive intelligence prevention

Example

Input
Result

"Is this better than OpenAI ChatGPT?"

Blocked

"I prefer using Claude instead"

Blocked

  • Configuration-based detection (customizable competitor list)

On outputs: Flags competitor mentions in AI-generated responses.

Output example

Input
Result

"You might want to try ChatGPT instead"

Blocked

References to competing products

Flagged

  • Configuration-based competitor detection

BanSubstrings Guardrail

Blocks messages containing specific words, phrases, or character patterns.

Direction

Input and output

What it catches

  • Custom blacklisted terms

  • Prohibited phrases

  • Specific keywords

  • Pattern matches (case-sensitive or insensitive)

Risk prevention: Enforces organization-specific content policies and filters domain-specific prohibited terms.

Use cases

  • Filter internal project codenames

  • Block specific terminology

  • Enforce custom content policies

Example

Input
Result

Messages with "confidential", "restricted", "internal only"

Blocked

  • Configurable: Define your own prohibited terms

  • Flexible: Case-sensitive or insensitive matching

On outputs: Blocks AI responses containing specific prohibited words or phrases.

Output example

  • Blocks responses with "confidential", "restricted"

  • Customizable term lists

  • Flexible pattern matching

Language Guardrail

Validates that messages are in expected/allowed languages.

Direction

Input and output

What it catches

  • Non-English content (when English-only required)

  • Unexpected language switches

  • Unsupported languages

Risk prevention: Ensures AI systems process only languages they're trained for, preventing poor-quality responses or misunderstandings.

Use cases

  • Language-specific applications

  • Compliance with localization policies

  • Service boundary enforcement

Example

Input
Result

"Bonjour, comment allez-vous?" (French when English required)

Blocked

  • Configuration: Define allowed languages

  • Automatic language detection

On outputs: Validates that AI responses are in expected languages.

Output example

Input
Result

French response when English required

Flagged

  • Automatic language detection

  • Multi-language support

Last updated