Security & Safety
Your AI managers read and analyze authorized accounts through AdvisorPPC's server-side API, within your plan's usage allowance. You never connect a personal model-provider login. Manual asks before every write. Bounded Auto runs only when an admin or owner chooses it and only for eligible reversible changes inside account guardrails. Budget and bid changes always wait for explicit approval.
How a change ships
Your manager studies your account, your spend, and your results. Reading is always safe. It changes nothing.
When it finds an improvement, it prepares the exact change as a draft, a dry-run you can inspect line by line.
Manual asks for your approval. Auto may continue only for an eligible reversible action inside guardrails you chose.
The action clears role, account and spending guardrails. Budget, bid and higher-risk changes still require your approval.
What is running today
Everything on this page is shipped and running now. Plain descriptions, no fine print.
Manual asks before every write. When an admin or owner selects Auto, only eligible campaign status and negative keyword changes can continue inside the selected account guardrails.
Budget changes, bid changes, OAuth grants, billing and higher-risk changes always require explicit approval.
Every write to an ad account passes a spend-cap check and a deny-by-default list before it runs. If a check cannot run, for any reason, the action is denied. When in doubt, the answer is no.
A broken safeguard stops the action. It never skips the check.
The keys that connect your ad accounts are encrypted before they are stored, a separately sealed secret for each customer. They are never saved in plain text.
Fernet symmetric encryption, applied before anything reaches the database.
If the service finds itself in an unsafe configuration, it refuses to boot rather than run with weak settings. Its database role also runs without superuser bypass, so even our own code has no shortcut around its limits.
Startup checks run before a single request is served.
Every account manager reads and analyzes freely. Manual stages each write for review. Optional bounded Auto can apply only eligible campaign-status and negative-keyword actions inside selected-account guardrails.
Budgets, bids and higher-risk actions always wait for you.
The principle underneath
Many services fail open: if a safeguard breaks, actions slip through. AdvisorPPC fails closed. If the spend-cap check cannot run, the write is denied. If the configuration looks unsafe, the service will not start. A broken safeguard stops work. It never skips the check.
Straight answers
Connect an account and watch them analyze it. Free stays read-only. On paid plans, Manual stays the default.
Questions about security? Write to hello@advisorppc.com.