Repository Docs & Knowledge Base

id: 8c4f1a72-6e3b-4d91-9f2a-3b7d1c6e5a88 name: Analyze kitchen performance kind: OperationalAnalytics cron: 0 0 8 * * * analysis_window: 90d comparison_periods: [7d, 28d]

Analyze kitchen performance to improve operational efficiency, reduce ticket times, and identify bottlenecks, error-prone stations, and service inefficiencies.

The process should evaluate kitchen workflow across stations, employees, and service conditions using historical operational data from the last 90 days only.

The output must contain kitchen performance insights only, without explanations or descriptions of methodology.

Known Tables & Columns

GNDSALE

• check (integer) - order identifier
• dob (date) - transaction date
• amount (decimal) - total check value
• timing signals - used for rush vs non-rush classification

GCHKINFO

• check (integer) - order identifier
• ticket time - preparation duration per order
• station - kitchen station responsible for preparation
• employee - staff member responsible for order
• error flags - preparation errors and issues

GNDITEM

• item (integer) - menu item identifier
• bohname (varchar) - item name
• category - menu category for aggregation

ITM

• id (integer) - menu item identifier
• longname (varchar) - item name
• station mapping - kitchen station assignment

Analysis Approach

Stage 1 — Ticket Time Analysis by Menu Category

Extract ticket time data from the last 90 days using GCHKINFO.

Aggregate:

• average ticket time per menu category
• ticket time variability
• slowest categories contributing to delays.

Stage 2 — Bottleneck Station Detection

Analyze station workload using GCHKINFO and ITM.

Identify:

• stations with highest average ticket times
• stations causing queue buildup
• structural bottlenecks in workflow between stations.

Stage 3 — Error Rate Analysis

Compute error rates using GCHKINFO error flags.

Aggregate by:

• station
• employee

Identify:

• highest error rate stations
• repeat-error employees
• correlation between workload and errors.

Stage 4 — Rush vs Non-Rush Performance

Use GNDSALE timing signals to classify periods into:

• rush
• non-rush

Compare:

• ticket times
• error rates
• station throughput

Identify degradation during rush periods.

Kitchen Optimization Insights

Kitchen Performance Dashboard:

• Average ticket time: 18 min (target: 15 min)
• On-time completion: 87%
• Error rate: 3.2%

Output Constraints

• Use historical data from the last 90 days only.
• Prefer aggregated summaries.
• Avoid more than 3 database queries unless necessary.
• Return kitchen performance insights only.
• Do not include explanations, reasoning, or methodology.

Output Format

Return structured kitchen performance results.

Example structure:

Kitchen Performance:

• Ticket Time:
• Category: Burgers → 12.4 min avg
• Category: Salads → 6.1 min avg

• Bottlenecks:
• Grill Station → highest delay contribution
• Fry Station → peak congestion periods

• Error Rates:
• Grill Station → 3.2%
• Employee A → 5.1%

• Rush vs Non-Rush:
• Rush: +35% ticket time increase
• Non-Rush: stable performance