Build a Predictive Facility Maintenance Work-Order Generator
Combine building operational runtimes and BMS telemetry with IFC equipment metadata to generate preventive work orders. Prioritize maintenance schedules based on component degradation thresholds.
What you are building
The core problem, expected build, and operating context for this challenge.
Combine building operational runtimes and BMS telemetry with IFC equipment metadata to generate preventive work orders. Prioritize maintenance schedules based on component degradation thresholds.
Operations & Maintenance Facility Supervisor
Extract equipment service records and parent building associations from IFC assets.
Ingest sensor operational hours and vibration telemetry streams.
Compare cumulative operating hours against manufacturer recommended servicing milestones.
Dispatch prioritized preventive maintenance work orders to facility dispatch queue.
Maintenance management console displaying equipment runtime progress bars, health scores, and work tickets.
Construct synthetic runtime logs matched against equipment GUIDs from sample IFC files. Starter examples below are synthetic. They are not downloaded records.
IfcOpenShell Extracts facility asset information utilizing IfcOpenShell ifcfm data export conventions.
crewai, pydantic, fastapi. CrewAI facilitates multi-agent delegation between equipment health evaluation and work-order scheduling roles. Reliable hosted or local language model capable of deterministic structured ticket generation.
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.
Correlates IFC asset GUID with incoming operating hour telemetry.
Generates work-order payload when running hours exceed 90 percent of service interval.
Calculates priority score based on system criticality and remaining runtime buffer.
```json [ { "input": { "asset_guid": "ASSET-CHILLER-01", "asset_name": "Centrifugal Chiller 1", "service_interval_hours": 2000, "current_run_hours": 1920, "criticality": "HIGH" }, "expected_output": { "generate_work_order": true, "priority": "URGENT", "runtime_remaining_hours": 80, "ticket": { "task": "Compressor lubrication and seal inspection", "due_within_days": 5 } } }, { "input": { "asset_guid": "ASSET-FAN-08", "asset_name": "Exhaust Fan East", "service_interval_hours": 1500, "current_run_hours": 420, "criticality": "LOW" }, "expected_output": { "generate_work_order": false, "priority": "NORMAL", "runtime_remaining_hours": 1080, "ticket": null } } ] ```
Dispatches maintenance drafts into simulated CMMS; does not directly trigger physical plant control overrides. Use mock external writes. Require human review before any real deployment.
Participation guide
Dispatches maintenance drafts into simulated CMMS; does not directly trigger physical plant control overrides. Use mock external writes and human review.
How work is evaluated
Correlates IFC asset GUID with incoming operating hour telemetry. Generates work-order payload when running hours exceed 90 percent of service interval. Calculates priority score based on system criticality and remaining runtime buffer.
Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Complete workflow
Extract equipment service records and parent building associations from IFC assets. Ingest sensor operational hours and vibration telemetry streams. Compare cumulative operating hours against manufacturer recommended servicing milestones. Dispatch prioritized preventive maintenance work orders to facility dispatch queue.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Correctness and evidence
Correlates IFC asset GUID with incoming operating hour telemetry. Generates work-order payload when running hours exceed 90 percent of service interval. Calculates priority score based on system criticality and remaining runtime buffer.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Review interface
Maintenance management console displaying equipment runtime progress bars, health scores, and work tickets.
Missing or incorrect.
Partly complete, with documented gaps.
Complete, with reproducible evidence.
Safe execution
Dispatches maintenance drafts into simulated CMMS; does not directly trigger physical plant control overrides.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Extract equipment service records and parent building associations from IFC assets.
Ingest sensor operational hours and vibration telemetry streams.
Compare cumulative operating hours against manufacturer recommended servicing milestones.
Dispatch prioritized preventive maintenance work orders to facility dispatch queue.
Reference links and supporting material
Construct synthetic runtime logs matched against equipment GUIDs from sample IFC files. Supplied starter examples are synthetic, not source extracts.
Challenge setup
Configuration summary for this challenge.
Challenge input
Input details are not configured.
crewAI
Multi-agent orchestration framework
Evaluated output
No output checks are configured.
- Extract equipment service records and parent building associations from IFC assets. Ingest sensor operation...
- Correlates IFC asset GUID with incoming operating hour telemetry. Generates work-order payload when running...
- Maintenance management console displaying equipment runtime progress bars, health scores, and work tickets.
- 2 public reference cases
- 1 configured tool
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- crewAI · Optional
Evaluation contract
- Complete workflow · Weight 40
- Correctness and evidence · Weight 30
- Review interface · Weight 20
- Safe execution · Weight 10
Reference cases
- 2 public reference cases
Workflow tasks
No workflow tasks are configured.
Recipe freeze marker
No recipe freeze time is recorded.