SLAs & SLOs

Venturi separates customer AI traffic from Venturi serving-plane availability. The gateway fails open for live AI requests; the serving-plane targets govern dashboard, query, export, and administrative surfaces.

What 99.9 does and does not mean

The 99.9% serving-plane target applies to Venturi's query and dashboard surface inside the customer environment. It does not describe the availability of your AI traffic, because the gateway forwards traffic even if Venturi attribution is degraded or unavailable.

Service objectives

Objective	Target	Scope
Gateway latency	50 ms P99 end-to-end budget	Decision-time observation path.
RAIL adapter timeout	20 ms wall-clock budget	Blocking model call where present.
Serving availability	99.9% target	Dashboard, query API, and exports.
Index freshness	P99 at or below 90 seconds target	Materialized attribution index.
Reconciliation latency	At or below 24 hours target	Reconciled-actual spend; the billable basis at coper ≥ 0.80.
Durability	RPO at or below 15 minutes; RTO at or below 1 hour target	Tenant attribution stores and event logs.

Targets are measured with named service-level indicators. Future or customer- specific commitments are written into the agreement that governs the deployment.

Error budgets

Error-budget review focuses on attribution availability and freshness. It never permits a change that would block customer AI traffic.