Talk to Fred is the WordPress AI voice assistant that captures leads, trains on your content, and stays compliant in 35+ regulated industries. Live in 20 minutes.
How It Works · Guardrails
AI is fast, confident, and helpful. That is exactly what makes it dangerous without discipline. Fred’s boundaries are enforced in code before Fred ever speaks, never just a prompt a clever question can talk around.
A human employee learns what not to say from compliance training and hard experience. An AI has no such instincts. It will cheerfully answer anything with authority, even when the right answer is “let me connect you with someone who can help.” Guardrails give Fred that judgment, and they are not optional equipment. Every Fred ships with them on. This is AI governance in practice: deciding in advance what an AI may do, and enforcing it.
Real visitors ask for things no business should let an AI answer. Here is how Fred handles three of them.
“Am I covered for that?” (insurance)
Only a licensed agent can bind coverage. An unguarded AI saying “yes, you’re covered” can put the agency on the hook. Fred explains coverage types in general terms, then books the visitor with a licensed agent, and your team gets the lead with the question attached.
“I’ve had a headache for three days, what is it?” (healthcare)
A diagnosis from a website widget is practicing medicine without a license. Fred does not guess, minimize, or reassure. It points the visitor to a qualified provider, offers to set the appointment, and escalates immediately if the language sounds like an emergency.
“What should I invest in?” (financial services)
A specific recommendation is regulated investment advice. Fred answers questions about how the firm works and what services cost, then routes the advice conversation to a registered professional, with the visitor’s details already captured.
The pattern is the same in all 50+ packs: answer what is safe, decline what is not, and hand the moment to a human before it becomes a liability. See the industry pages for the exact rules in your trade.
Talk to Fred.
In code, before and after the AI runs. In Fred Cloud, that happens on our servers. In the WordPress plugin, it happens inside the plugin on your own hosting, your rules running on your own infrastructure. Either way the rules are checked in code, not suggested in a prompt. That distinction is the whole product: a prompt is a request the AI can be argued out of, an enforced rule is a boundary it never gets to cross. Nothing about the rules lives in the visitor’s browser, so there is nothing on the page to tamper with.
Yes, and it is the practical kind. AI governance means deciding in advance what an AI is allowed to do, enforcing those decisions, and being able to prove it afterward. Fred ships all three: enforced rules with severity levels, escalation paths to humans, your own policies stacked on top, and an audit trail your compliance reviewer can inspect. Most chatbot vendors hand you a prompt box and call it policy.
The boundaries do not depend on the AI’s judgment in the moment, which is what fails when someone roleplays, hypotheticals, or “just asking for a friend”s their way past a prompt-based bot. Fred is architected to reduce preventable failure modes, and the rules apply no matter how the question is dressed up.
A polite, on-brand redirect with a next step: who to talk to, how to book, or how to reach help. Never a scold, never a wall of legal text. Declining gracefully is part of the product; the visitor should feel served, not rejected.
Rules written for how your industry is regulated: what to decline, what to escalate to a human, what disclosures matter, and how to respond when the topic comes up. Severity levels decide whether Fred redirects gently or hands off immediately. Each industry page shows the live rules in its pack.
Crisis and emergency language is treated as the highest severity. Fred surfaces the right resource, like the 988 crisis line for self-harm language, and escalates to your team the way you configure it. A life comes before a lead, always.
Yes. You can see what was declined or escalated and why, so your compliance reviewer is not taking our word for anything. That audit trail is part of the trust story.
Every install can stack custom rules on top of the packs: things you never want discussed, phrases that must trigger a handoff, topics reserved for specific staff. Our training videos walk you through it, or add a paid setup and we configure it with you.
Pick your industry pack, add your own rules, and go live in about 20 minutes. The boundaries are on before the first visitor says hello.
