CT-05
Bimodal Distribution
Cycle Time
Default severity: medium
ProcessMetricsOutputRisk
What it detects
Two distinct clusters of completion times exist — indicates two fundamentally different work types tracked on one board. Cluster separation threshold is configurable.
Detection formula
Run k-means(k=2) on cycle_times IF cluster_separation > config.ct.bimodal_separation_stddev * stddev // default: 2 THEN FLAG bimodal — recommend separate boards per work typeExamples in practice
- Resolved items cluster around 2-day and 18-day completion times on the same board.
- K-means separation shows two distinct completion-time clusters instead of one flow shape.
- The board mixes quick operational fixes with multi-week feature work under one metric.
Suggested response
Review cycle-time drivers on the cited work items; tighten WIP or handoffs where delays repeat.
Coaching playbook
Symptom
Two distinct clusters of completion times exist — indicates two fundamentally different work types tracked on one board. Cluster separation threshold is configurable.
Why it matters
When "Bimodal Distribution" keeps appearing, the team is signalling a repeatable process gap. Left unexamined, the pattern hides where work really stalls and makes improvement metrics harder to trust.
What you can achieve
Review cycle-time drivers on the cited work items; tighten WIP or handoffs where delays repeat.
Facilitation questions
- What system change would stop "Bimodal Distribution" from firing again?
- What do the cited issues have in common — same root cause or same workaround?
- Who owns the two-week experiment and how will we verify on the next import?
Run this rule against your own tracker data with Flow Analyzer.