In short: Compliance is a setting on the agent, not a paragraph in the prompt hoping to be obeyed.
Definitions
- Policy pack
- A ready-made set of rules for regulated work, with the stricter rules locked on rather than left to configuration.
- Calling hours
- The window, in the customer's own time zone, within which a call may be placed. Enforced before the call, not after.
- Audit trail
- A tamper-evident record of who changed what.
How it works
The guard sits between the model and the voice, so a rule breach is stopped before it is spoken, not flagged afterwards. Floors in a regulated pack cannot be relaxed from the console; relaxing one requires an audited override.
The controls
- Say it's an AI: a switch that makes the agent state it is an AI before it starts.
- Calling hours per agent, in the customer's own time zone, enforced before a call is placed.
- A daily cap per number, so nobody is called five times in a day by accident.
- Opt-out honoured during the call: a caller asking not to be called again is recorded as such the moment they say it.
- Sensitive details protected in speech: long numbers and one-time codes are masked rather than read aloud, and identity can be required before any account detail is discussed.
- Ready-made policy packs for regulated work, with the stricter rules locked on.
- Retention and erasure: recordings and transcripts age out on your schedule, and a caller's data can be erased on request.
- An audit trail of who changed what, tamper-evident.
Related questions
How does CallWhiz AI handle compliance?
Compliance is a setting on a CallWhiz AI agent, not a paragraph in the prompt: a switch that makes the agent say it is an AI before it starts, calling hours enforced in the customer's own time zone before a call is placed, a daily cap per number, opt-outs honoured the moment a caller asks, masking of long numbers and one-time codes in speech, ready-made policy packs for regulated work with the stricter rules locked on, retention and erasure on your schedule, and a tamper-evident audit trail.
Does the agent tell callers it is an AI?
A CallWhiz AI agent can be set to state that it is an AI before it starts, with a single switch on the agent. The guard that enforces rules like this sits between the model and the voice, so a breach is stopped before it is spoken rather than flagged afterwards.
Does my call data leave my network?
It does not have to. The same platform runs inside your own cloud account or on your own hardware.