Safety and escalation

An AI answering your phone is only worth having if it never embarrasses you. StrandCalls ships a set of hard guardrails that no setting, instruction, or caller pressure can turn off.

What the AI will never do

• Invent a price. Quotes come from your service catalog as a structured lookup, read back. No catalog entry, no number.
• Invent an ETA. It states arrival times only after you’ve given one. See Emergency dispatch.
• Book an emergency for next Thursday. Urgent calls go through the dispatch loop, not the calendar.
• Play doctor, electrician, or lawyer. For anything with a safety or legal dimension it follows the script and escalates rather than diagnosing.
• Re-ask what it already knows. Returning callers aren’t made to repeat their address.

Per-trade safety scripts

Your trade type in Settings → Business Profile selects the safety scripts the AI runs. These are the “before anything else, do this” moments. Three are active today:

• Plumbing — coaching the caller to the shutoff valve before anything else.
• Electrical — kill the breaker; never diagnose over the phone.
• HVAC — a short vulnerability triage on any no-heat or no-cool call (who’s in the home, the indoor temperature, whether there’s a safe backup) so a no-AC call with an elderly resident isn’t treated like a routine one.

Additional scripts for locksmith / towing, garage door, and pool / pest trades ship with the product and switch on automatically once those trades become selectable at signup. The locksmith script carries the life-safety rule that matters most: a child or pet locked in a hot car gets 911 first, every time, before any conversation about service.

Review and adjust the scripts for your business in Settings → Safety & Escalation.

The escalation guarantee

When the AI is out of its depth, the correct behavior is to stop and get you — not to improvise. Escalation is a guaranteed path: the call produces a message, a notification, and a record, rather than a confident wrong answer.

This is why “I’ll have the owner call you back” is a feature. It is the honest ceiling of what a receptionist should decide alone.

Owner-verified fact sheets

For statements that carry legal or contractual weight — licensing, insurance, warranty terms, service-area claims — the AI reads from fact sheets you have explicitly verified, not from anything it inferred. Fact sheets are managed in Settings → Safety & Escalation.

If a caller asks something no fact sheet covers, the AI escalates rather than answering.

Recording and consent

Calls are recorded so you get transcripts. Consent handling is built into the call flow. If your state or your customers require a specific disclosure, raise it with support — this is not something to improvise in custom instructions.

Never tier-gated

Every safety script, the escalation guarantee, and emergency dispatch ship identically on every plan. Charging more for safety would be a moral hazard; it isn’t a lever we pull.

Auditing what actually happened

Read transcripts in Calls. Every quote the AI gave is logged, every escalation is recorded, and every dispatch has a state history. If you ever suspect the AI said something it shouldn’t have, the evidence is there — and it’s worth telling support about.