Spend caps, receipts,
and reconciliation for AI runs
Uncontrolled AI execution is a financial and operational risk. Decisionproof turns AI runs into budget-bounded, auditable, settlement-safe operations — with hard spend caps, receipt-backed cost settlement, and a reconciliation loop that rolls every run forward or back, deterministically.
$29 / 30 days — PayPal only — no auto-renewal
Hard spend caps
Submit each run with a max cost. Budget is reserved before work starts — runs that would exceed the cap are rejected, not truncated.
Receipt-backed settlement
Cost settles only when the result artifact is written and its metadata is captured. No receipt means no settlement.
Automatic reconciliation
A continuous loop scans for lease expiry, stuck finalize stages, and missing receipts, and rolls each run forward or back without silent money drift.
Exportable audit trail
Every run is recorded as input → state transitions → result → settlement, and exportable at any time. No TTL on the data.
API-key auth
Create and revoke keys from your dashboard. No SDK required. No OAuth flows to manage.
Tenant data isolation
Your run data is scoped to your workspace. API keys only authorize access to your own tenant's runs and receipts.
Not an agent framework. The control layer you run around it.
Agent frameworks, durable execution engines, and orchestration toolkits cover how an AI run is constructed and resumed. Decisionproof sits one layer up: it governs what a run is allowed to spend, how completion is proven, and how cost settles when a worker crashes, a lease expires, or a retry collides.
Treat each run as an accountable economic transaction. Decisionproof handles the money, the receipts, and the recovery — so your AI stack clears cleanly, even on the bad days.
Ready to try it?
Paid private beta — $29 for 30 days, 1,000 decision credits included, no auto-renewal.
Get started