Skip to main content
Back to challenges
Challenge

Orchestrate Plug-and-Produce MTP Factory Rescheduling with LangChain and OpenRouter

Modular Type Package (MTP) standardization enables modular process plants to reconfigure production modules dynamically for 'plug-and-produce' automation. However, when a modular equipment asset fails or a new order arrives, plant schedulers must dynamically reallocate process modules without violating material, labor, or machine setup constraints. In this challenge, you will construct a dynamic factory rescheduling agent using LangChain (LangGraph) and OpenRouter for multi-model model orchestration. The agent will monitor MTP module state descriptions, re-route process execution workflows, and produce optimized work order sequences to minimize factory downtime.

EngineeringHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build an MTP dynamic factory scheduling graph using LangChain/LangGraph and OpenRouter.

Delivery guide

How work is evaluated

Evaluation

Evaluates the agent's graph execution in producing valid, constraint-compliant dynamic factory rescheduling outputs upon module failure events.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

schedule_feasibility_test

Checks that output schedule contains no double-booked MTP modules.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

scheduling_efficiency

Measures total throughput loss minimization score • target: 88 • range: 0-100

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Build a stateful multi-agent workflow with LangGraph for modular plant scheduling.

  • Integrate OpenRouter as a unified multi-LLM routing layer for constraint analysis.

  • Parse MTP (Module Type Package) state manifests and operational capabilities.

  • Solve scheduling allocation problems under material and module availability constraints.

Resources and assets

Reference links and supporting material

Dataset notes

Modular Type Package (MTP) manifest files, module state transition tables, and work order scheduling queues.

Challenge setup

Evaluates the agent's graph execution in producing valid, constraint-compliant dynamic factory rescheduling outputs upon module failure events.

Challenge input

JSON with list of active MTP modules, active work order queue, and failed module alert

LangChain

Offers structured tool integration and stateful graph management via LangGraph.

OpenRouter

Provides unified API access to multiple LLM providers for reasoning and scheduling.

Evaluated output

JSON containing rescheduled_timeline, active_modules, and bottleneck_warning

Evaluation checks
  • Checks that output schedule contains no double-booked MTP modules.
  • Measures total throughput loss minimization score • target: 88 • range: 0-100
Configured evaluation evidence
  • Benchmark: Operations Research & Production Scheduling Benchmark
  • Scheduling Efficiency target: 88
  • 1 public reference case
Configured runtime
  • 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

Action Space
  • Langchain · Required
  • LangChain · Optional
Policy Serving
  • OpenRouter · Optional
Orchestration
  • Langchain · Required
  • LangChain · Optional
  • OpenRouter · Optional

Evaluation contract

  • schedule_feasibility_test · Weight 1
  • scheduling_efficiency · Weight 1

Metrics

  • scheduling_efficiency · Target 88

Benchmarks

  • Operations Research & Production Scheduling Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with list of active MTP modules, active work order queue, and failed module alert

    Output: JSON containing rescheduled_timeline, active_modules, and bottleneck_warning

    Execution harness: Python

Evaluation tools

  • LangChain · agent_framework
  • OpenRouter · llm_gateway

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Orchestrate Plug-and-Produce MTP Factory Rescheduling with LangChain and OpenRouter