Repository Docs & Knowledge Base

Consolidated Spensara documentation repository (722 Markdown & architecture documents in ../repository)

Operational monitoring, alerting, anomaly detection, and health specifications.

monitor-specs/backend/Kds.Ai.Data/MonitorSpecs/prep-time.md 1,688 bytes · Updated Oct 23, 2026 10:44 AM EDT

Raw File

id: 019cb9fd-1497-75ff-a497-3515bc4c5895 name: Prep Time Monitor kind: Anomaly cron: 0 0 * * * * analysis_window: 1h comparison_periods: [1d, 7d]

Analyze order preparation time anomalies using the curated.kitchen_orders table.

Known Table Columns

preparation_time (int, seconds, nullable) - how long the order took to prepare
create_time (int, unix timestamp) - when the order was created
store_guid (varchar) - which store/restaurant
items_count (int) - number of items in the order
order_type (varchar) - type of order (dine-in, takeout, delivery)
destination (varchar) - kitchen station
done (tinyint) - whether the order is complete
is_deleted (tinyint) - soft delete flag

Query the last {AnalysisWindow} of completed orders (done=1, is_deleted=0, preparation_time IS NOT NULL).
Verify that the analysis window contains at least 20 completed orders. If not, call emit_no_anomaly — the sample is too small for reliable analysis.
Aggregate by hour to get hourly average prep times.
Compare against the historical baseline (same hour of day {ComparisonPeriods}).
Flag hours where the average prep time deviates significantly (>3 standard deviations) AND the absolute deviation is at least 60 seconds above the baseline average.
Optionally break down by order_type or destination to find more specific patterns.

Low: 3-4 sigma deviation AND at least 60s absolute increase
Medium: 4-5 sigma deviation AND at least 120s absolute increase, sustained across 2+ consecutive hours
High: >5 sigma deviation AND at least 180s absolute increase