Politeness is the product, and most of it is built in: every agent the Builder creates carries a floor of behaviour that cannot be accidentally removed. This page explains those defaults and the small part that remains the operator's.
This page describes product behaviour, not legal advice. Rules on AI disclosure, call recording and outbound calling vary by where and how an organisation operates — operators should check their own obligations.
Callers always know it's an AI
An agent's first words disclose that it is an AI, woven into the greeting. Agents never impersonate a person, borrow a real staff member's name, or clone a voice. The full set of guarantees is in What every agent promises your callers.
Card numbers: never spoken, never keyed
Agents will not take payment card details on a call — not by voice, and not by keypad, because keyed digits land in the call record like everything else. The agent routes payment to a secure channel the operator defines — a person, a payment line, an emailed link — and if a caller tries to hand over card details anyway, the attempt is flagged for follow-up.
A human is one ask away
Every team the Builder designs includes a defined path to a human — see Teams, transfers & subagents. When the agent doesn't know something, it says so and offers an alternative. A caller in distress is signposted to the right help; an abusive caller gets one warning, then a polite end to the call.
Recording, with callers in the know
Recording is optional and per-agent — when it is on, recordings are stored encrypted and any call can be reviewed afterwards. The agent's generated instructions include a recording notice so callers hear about it up front; keeping that notice in place is the operator's side of the bargain.
Outbound calls people actually want
polite.ai is inbound-first by design. There is no dialler and no scheduler — an outbound call happens only when the operator's own system requests one through the API, and every destination passes an outbound filter before it is dialled.
Outbound works best where the recipient expects the call and the agent arrives with context: reminders for tomorrow's appointments, promised callbacks, order-ready notifications. Cold-calling strangers with an AI is neither what the product is built for nor a good idea. One honest limitation: agents can't reliably detect answering machines, so the agent's instructions should say what to do if the call sounds like voicemail.