Guardrails, by industry.

What guardrails are

Guardrails are rules that constrain what Fred will and will not say. They keep Fred from giving advice outside its scope, making claims that create liability, or drifting into regulated territory. They are enforced in code, before and after Fred speaks, not suggested in a prompt that a clever question can talk around.

How they work

You select the packs that match your industry. Fred checks every response against the active rules before it reaches the visitor, and adjusts or declines when something would cross a line, offering a safe next step such as connecting a qualified person.

Always on, for every business

• No discrimination or harassment
• No requests for sensitive personal data Fred has no business collecting
• No fabrication, Fred answers from your content and says so when it does not know
• No impersonation, Fred always identifies as an AI

45+ industry packs

Packs cover healthcare, financial services, legal, insurance, real estate, home services, and many more. Healthcare guardrails keep Fred from diagnosing or accessing records, financial guardrails keep it from recommending securities or projecting returns, and legal guardrails keep it from giving legal advice. Each can handle the safe parts, like scheduling and general information, and hand off the rest.

Custom rules on top

Beyond the packs, every install can add custom guardrails: block specific topics, require disclosures, route sensitive subjects to a human, or customize the redirect language. Fred can even propose new guardrails from real conversation patterns for you to review.

An honest clarification

Guardrails are conversation boundaries, not regulatory certifications. HIPAA guardrails help you avoid inappropriate health conversations, they do not make your site HIPAA certified. Always consult qualified professionals for compliance in your industry.