Motor Control Center Automated Estimator with OpenAI Agents SDK and Cerebrium
Motor control center (MCC) engineering and configuration leads to long delivery lead times due to manual bill-of-materials generation. Implement an automated MCC configurator using OpenAI Agents SDK deployed on Cerebrium to generate BOMs and wiring diagrams from single-line drawings. Reduce design review iteration time by 80%.
What you are building
The core problem, expected build, and operating context for this challenge.
Build an automated motor control center estimation pipeline using OpenAI Agents SDK deployed serverlessly on Cerebrium.
How work is evaluated
Evaluate the correctness of the generated MCC Bill of Materials given standard motor power and control requirements.
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_bom_coverage
All input motors have corresponding control gear in output
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
bom_accuracy
Accuracy of component rating selection • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Deploy an OpenAI Agents SDK worker on Cerebrium serverless infrastructure
Parse single-line diagram specs into structured motor control center (MCC) requirements
Generate valid Bills of Materials (BOM) including circuit breakers, starters, and VFDs
Evaluate lead-time reduction and accuracy against industry benchmarks
Reference links and supporting material
Load lists and electrical specifications for 30 motor control center configurations.
Challenge setup
Evaluate the correctness of the generated MCC Bill of Materials given standard motor power and control requirements.
Challenge input
JSON array of motor loads with HP, voltage, and starter type requirements
OpenAI Agents SDK
Agent building framework with tools.
Cerebrium
Serverless container execution host for low-latency agent hosting.
Evaluated output
JSON object with bom_items list containing component descriptions and part numbers
- All input motors have corresponding control gear in output
- Accuracy of component rating selection • target: 0.95 • range: 0-1
- Benchmark: Electrical Systems BOM Generation Benchmark
- Bom Accuracy target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
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
- OpenAI · Required
- Cerebrium · Optional
- Azure OpenAI Service · Optional
Evaluation contract
- complete_bom_coverage · Weight 1
- bom_accuracy · Weight 1
Metrics
- bom_accuracy · Target 0.95
Benchmarks
- Electrical Systems BOM Generation Benchmark
- energy
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON array of motor loads with HP, voltage, and starter type requirements
Output: JSON object with bom_items list containing component descriptions and part numbers
Execution harness: Python
Evaluation tools
- OpenAI Agents SDK · Agent Framework
- Cerebrium · Inference Runtime
Recipe freeze marker
No recipe freeze time is recorded.