Guardrail Policies
A Guardrail Policy is the set of limits you put around the engine. It is versioned, visible, and auditable — and enforced in code. The engine cannot propose, let alone execute, a change that falls outside it.
Maximum bid and budget moves per action, a daily spend movement cap, and a cap on the number of actions per run. Protected brand terms, protected campaigns, and protected ASINs the engine must never touch. No-pause and no-negative lookback windows that shield recent converters. A minimum confidence threshold. And, for auto-approval, exactly which action types are eligible and the confidence they must clear.
Every action in a Manifest is checked against your policy. An action can pass, be clamped to your cap (a proposed bid jump trimmed to your maximum), or be blocked entirely. Blocked and clamped actions are shown to you with the reason — nothing is silently dropped or silently applied.
Each run records the Guardrail Policy version it used. Change your policy and the new version applies to future runs, while the history is preserved — so you can always see which rules were in force for any past execution.
Because Shadow Mode runs the full pipeline without executing, it's the right place to test a new policy: adjust the limits, run analysis, and watch how the Manifest changes — with zero risk to your account.
At a glance
Get started
Start in Shadow Mode for free, or take Hosted Starter for a 30-day trial — approve from Telegram, execute safely, reconcile everything.