Help center

Our approach to AI safety.

Most conversational AI either runs with no guardrails or bolts on one filter. Fred is built in layers, and every answer is checked before and after the model runs.

The problem with most AI assistants

Most conversational AI either runs with no guardrails and hopes for the best, or bolts on a single content filter and calls it compliance. Neither holds up when the AI is talking to your customers about coverage, medical questions, legal matters, or money.

Checked before and after

Fred evaluates every message against your active rules before the AI processes it, and evaluates the AI’s response again before it reaches the visitor. If something should not be answered, it is intercepted. If the model produces something that crosses a line, it is caught and corrected. The AI never gets the last word unchecked, and it is all enforced in code.

Layered, not a flat list

Guardrails are composed in layers: universal safety rules for every conversation, then regional, industry, and your own custom rules on top. A healthcare practice in California gets different boundaries than a roofing company in Texas, resolved automatically from your configuration. Each rule defines what happens when it triggers, from adding a disclaimer to redirecting to a professional, flagging for review, or redacting, proportional to the risk.

Proactive, not just reactive

Compliance boundaries are built into Fred’s instructions from the first word of a conversation, so the goal is not to generate a bad answer and then fix it, it is to not go there in the first place. The after the fact check is the safety net, not the main mechanism.

Practical certainty

Academic research chases mathematical certainty for AI outputs, mostly in the lab. Fred solves the same problem from the practitioner side, with layered rules, before and after checks, and pattern based detection, running in production on real sites today. The real threat is not a researcher probing edge cases, it is a visitor asking a medspa bot for a diagnosis, and Fred handles that.

What it means for you

You do not need to understand any of this to use Fred. You pick your industry, enable the packs, and Fred handles the rest. If you are evaluating Fred for a regulated business and want a deeper walkthrough, book a call.

Keep reading.

Practical guardrails

Real examples of what goes wrong without guardrails, by industry.

Read more →

Industry compliance

45+ guardrail packs and what they keep Fred from saying.

Read more →

Privacy and data

Where data goes, what gets redacted, and exactly what you control.

Read more →

Evaluating Fred for a regulated business?

Book a call and we will walk through the compliance layers for your industry.