Cost anomalies

Overview

Detect changes in volume, context, retries, escalation, route mix, and provider unit economics.

• Select the accountable organization and project.
• Use one explicit measurement window.
• Preserve route and provider attribution.
• Compare cost with quality, latency, and success evidence.
• Label projections and measured values separately.

Production checklist

• Keep credentials in a server-side secret store.
• Set explicit cost, latency, privacy, provider, and regional constraints.
• Capture route and evaluation evidence for incident review.
• Test timeouts, cancellation, fallback, and denied-policy paths before rollout.