{"stable_id":"23a3326b0ffa1d4b","slug":"boston-bird-school-bus-routing","company":"Boston Public Schools","workflow_name":"BiRD system-level school-bus route optimization","function_code":"enrollment","pattern_codes":["coordination_compression","creator_to_judge"],"changed_assumption":"Routes can be optimized as one district system instead of built school by school and then combined.","evidence_strength":"verified","publication_tier":"showcase","freshness":"current","reviewed_at":"2026-08-23","updated_at":"2026-08-22","source_quality_summary":"1 independent, 1 peer reviewed; publication outcomes are verified.","caveat_summary":"Implemented operational result reported by the peer-reviewed design team; not a randomized trial.","freshness_caveat":null,"workflow_summary":{"before":[{"actor":"Human transportation routers","action":"Build and maintain routes manually for each school over multiple weeks.","actor_type":"human"},{"actor":"District planners","action":"Connect school-level routes and assign buses.","actor_type":"control"}],"hinge":"Routes can be optimized as one district system instead of built school by school and then combined.","after":[{"actor":"BiRD optimization algorithm","action":"Generates district-wide student stops, route sequences, and multi-school bus reuse in about 30 minutes.","actor_type":"ai"},{"actor":"Human routers","action":"Review and adjust the optimized base plan for operational exceptions.","actor_type":"human"}],"decision_mode":"retained","decision_marker":"Human authority remains at the consequential boundary"},"before":[{"order":1,"actor":"Human transportation routers","action":"Build and maintain routes manually for each school over multiple weeks.","handoff_to":"District route plan","control":"Local school and vehicle constraints"},{"order":2,"actor":"District planners","action":"Connect school-level routes and assign buses.","handoff_to":"Drivers and families","control":"Manual system reconciliation"}],"after":[{"order":1,"actor":"BiRD optimization algorithm","action":"Generates district-wide student stops, route sequences, and multi-school bus reuse in about 30 minutes.","handoff_to":"Human routers","control":"Ride-time, accessibility, vehicle, and policy constraints"},{"order":2,"actor":"Human routers","action":"Review and adjust the optimized base plan for operational exceptions.","handoff_to":"Drivers and families","control":"District retains final plan authority"}],"decision_rights":"The optimizer proposes a feasible system plan; district staff approve and modify routes.","exception_path":"Human routers adjust for wheelchair vehicles, door-to-door service, monitor needs, student conflicts, and operational knowledge.","removed_work":["Multi-week manual generation of the base route map","Redundant buses created by school-by-school optimization"],"outcomes":[{"metric":"Buses and annual operating cost","baseline":"Approximately 650 buses in the manual solution","result":"50 buses removed in the first implementation year and about $5 million saved, with average ride time remaining about 23 minutes","period":"Fall 2017 implementation","scale":"Boston Public Schools district routing across public, private, and charter schools","attribution_caveat":"Implemented operational result reported by the peer-reviewed design team; not a randomized trial.","evidence_label":"verified"}],"executive_lesson":"The breakthrough was changing the unit of optimization from each school to the whole district, then positioning human routers as exception designers rather than route constructors.","anti_pattern":"Optimizing only cost while ignoring ride time, accessibility, and family-level constraints.","questions_for_leaders":["Are teams optimizing locally against a system-wide objective?","Which exceptions must remain explicit constraints?"],"collections":["human-still-decides","queue-eliminated"],"bundle_version":"1.0.0","bundle_fingerprint":"sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93","canonical_url":"https://brianletort.ai/transformations/boston-bird-school-bus-routing"}