Help topic

Trust & how it works

Control boundaries, memory, and claim safeguards.

TRUST-1

What Deloosh does on its own — and what it always asks first

Deloosh watches sending health, records activity, and raises governed decisions on its own, while drafting, editing, scanning, and account controls start only when you ask. Nothing in the Deloosh app or assistant sends email: “Approve & draft” produces a draft, and SEND-1 explains the product’s per-send approval commitment.

TRUST-2

Why the AI won't make things up

Deloosh is built to prefer a visible gap or refusal over plausible-sounding fiction. Performance and deliverability claims need explicit proof, images come only from your library, and uncertain reasoning stays labeled as uncertain.

TRUST-3

What Deloosh remembers after each campaign

After a campaign goes quiet, Deloosh writes itself one short, factual memory of what happened — grounded strictly in your sending ledger. It is not a report you read; it is how the advice you get next time gets better.

All help topics