Decision intelligence platform for safe, automatic ad decisions

Context packs encode how you think about ads — your economics, funnel, creative and risk logic — as reusable knowledge the AI agents follow. Rules are deterministic templates like “stop losers” or “scale winners.” You activate the packs and rules that fit an account, and they compile into the workspace that drives every decision, so the system applies your playbook instead of a generic one.

Only if you let it. By default every decision waits in a review queue for you to approve, reject or override. When you trust the system on a given scenario, you can enable Auto Mode so it executes on its own — and you decide exactly which scenarios that applies to, while everything else keeps waiting for a human.

No. AI agents read live metrics and produce signals, but the final decision is made by a deterministic rule engine with a priority matrix, guards and your thresholds. Every decision — stop, scale, reduce or wait — comes with the reason and the threshold that triggered it, and it accounts for cohort maturity so it won’t stop a cohort before it has had time to pay back. The same inputs and thresholds produce the same call every time.

Actions run through a safe gateway, never directly. Everything is written to an audit log, a kill switch halts all automation instantly, and one-click rollback restores the last stable budget. Scaling steps are gradual and watched after the fact, so a bad move can be undone rather than compounded by the next one.

From your own warehouse — hundreds of ad, order and cohort metrics refreshed every few minutes. The agents analyze that live data and the decisions execute against the connected ad platform, so what you see and what the system acts on are the same source of truth.

Platform access is free, managed spend carries a 1% fee with no subscription, and AI generation is billed in tokens rather than a fixed plan.

Every execution passes through a safe gateway with a full audit log and one-click rollback, so nothing changes in an ad account without a traceable reason. This is the engine that powers Campaign Autopilot, and it reads the same free attribution and predictive LTV data as the rest of the platform, so decisions follow real payback rather than platform-reported conversions.

Encode your context and rules, let AI agents read your live metrics, and get one clear decision per campaign — stop, scale, reduce or wait — with the reasoning to back it. Approve each action yourself or switch on Auto Mode, always behind a safe gateway with a full audit log and one-click rollback. This is the decision engine that powers Campaign Autopilot. Your knowledge plus live data flows through a pipeline you can see end to end: contexts and rules, AI analysis, one deterministic decision, your approval, and safe execution with an audit trail. Every stage keeps its inputs visible, so a decision traces back to the rule and the number behind it.

The log keeps decision, threshold and resulting change together, which is what makes a bad week reviewable.