Runtime action event
Your tool reports the action before it runs.
Orbit Authority Action Control
For payments, trades, and AI-built app side effects, Orbit Authority checks whether the actor has permission, whether the action is in scope, and whether approval is required.
Orbit does not replace Stripe, your broker, or your app. It is the decision point before those systems are called.
See Action ControlActor requests a consequential action.
workflow: send an $8,000 payout
Orbit Authority checks authority and scope.
policy: over your $5k limit, identity verified
Allow, escalate to a human, or deny.
Asks you first, before the payout goes out.
Receipt and audit trail recorded.
A signed receipt records who, what, the policy, the decision, and who approved.
Decision chain
Action Control is not just a log. Where ORBIT can block before the action runs, it does; where it can only watch, it says so.
Your tool reports the action before it runs.
ORBIT turns the action into one standard record — who, what, which account, and which policy applies.
Your policies combine safely: the strictest rule wins, anything uncertain gets escalated, and a standing approval can never grant more than the base policy allows.
The result is allow, ask, or block, with a signed receipt.
ORBIT blocks a risky action before it runs where it can, and only watches where it can’t, keeping a signed audit trail either way.
Each request resolves to a clear decision — allow, ask, or block — and leaves a signed receipt an operator or auditor can read.
/payments
Let routine billing work run, but stop or escalate anything outside amount, merchant, account, or actor scope before Stripe is called.
| Action requested | Decision | Why | Receipt says |
|---|---|---|---|
| refund.create USD 250 | ALLOW | Under $500 standing refund approval. | Receipt says refund was authorized by standing approval before execution. |
| payout.create USD 8,000 | ASK | Above your $5k limit; needs your approval. | A signed receipt records who, the account, the amount, the policy, and who approved. |
| charge.create USD 12,400 | BLOCK | Merchant and invoice scope do not match the active workflow. | Denial receipt records the failed scope check; money never moves. |
/trading
Put mandate, exposure, asset-class, drawdown, and market-hours limits between the model and the broker execution path.
| Action requested | Decision | Why | Receipt says |
|---|---|---|---|
| trade.execute NVDA $42,000 | BLOCK | Order exceeds trading mandate. | Denial receipt captures instrument, notional, mandate version, and circuit-breaker state. |
| position.close TSLA 15% | ALLOW | Risk-reduction action inside existing position scope. | Authorization receipt proves the close was evaluated before the broker call. |
| trade.execute BTC perpetual | ESCALATE | New asset class requires a mandate exception. | Escalation receipt names the requested exception and timeout fallback. |
/apps
Give AI-built products a runtime checkpoint before customer records, emails, plans, or destructive app mutations become real.
| Action requested | Decision | Why | Receipt says |
|---|---|---|---|
| db.users.updateMany plan=enterprise | ESCALATE | Bulk customer mutation requires human review. | Receipt links the mutation shape, table scope, policy, reviewer, and decision. |
| send campaign to 18,420 users | ESCALATE | External communication crosses volume threshold. | Receipt records audience size, template hash, sender authority, and approval path. |
| delete account acct_9K2 | BLOCK | Destructive action lacks verified customer request. | Denial receipt proves the delete was blocked before application state changed. |
Policies can include actor identity, account scope, amount, instrument, merchant, time window, region, standing approval, timeout, and default-deny behavior. Harmless work moves fast. Risky actions hit approval, policy, or a hard stop.