Skip to main content
Back to challenges
Challenge

Custom Food Processing Line Orchestration with CrewAI Agents

High-speed customized food processing lines suffer throughput drops due to uncoordinated batch adjustments between frying and freezing stages. Build a multi-agent orchestration team using CrewAI to continuously adjust conveyor speeds and temperature parameters. Maximize line yield while reducing product giveaway by 15%.

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.

Orchestrate specialized CrewAI role-playing agents (Frying Agent, Freezing Agent, Quality Agent) to optimize custom chicken nugget production parameters.

Delivery guide

How work is evaluated

Evaluation

Measure food processing line optimization results output by CrewAI crew against line efficiency benchmarks.

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

giveaway_threshold_pass

Giveaway percentage below 1.5% limit

Binary check

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

Dimension 2

giveaway_reduction_pct

Reduction percentage in weight giveaway • target: 15 • range: 0-30

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

  • Design a multi-agent CrewAI system with distinct operational roles (Fryer, Freezer, QA)

  • Implement collaborative tasks with sequential and hierarchical process execution

  • Optimize line speed vs cooking temperature trade-offs dynamically

  • Reduce product giveaway weight variance by 15% in simulated test runs

Resources and assets

Reference links and supporting material

Dataset notes

Batch processing measurements for custom food production lines (batch weight, dwell times, moisture levels).

Challenge setup

Measure food processing line optimization results output by CrewAI crew against line efficiency benchmarks.

Challenge input

JSON with target_throughput_kg_hr, ambient_temp_c, raw_batch_weight_g

CrewAI

Provides structured role-playing multi-agent workflow framework.

Evaluated output

JSON with fryer_temp_c, fryer_speed_m_min, freezer_temp_c, estimated_giveaway_pct

Evaluation checks
  • Giveaway percentage below 1.5% limit
  • Reduction percentage in weight giveaway • target: 15 • range: 0-30
Configured evaluation evidence
  • Benchmark: Food Processing Yield Optimization Benchmark
  • Giveaway Reduction Pct target: 15
  • 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
  • CrewAI · Required
  • crewAI · Optional

Evaluation contract

  • giveaway_threshold_pass · Weight 1
  • giveaway_reduction_pct · Weight 1

Metrics

  • giveaway_reduction_pct · Target 15

Benchmarks

  • Food Processing Yield Optimization Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with target_throughput_kg_hr, ambient_temp_c, raw_batch_weight_g

    Output: JSON with fryer_temp_c, fryer_speed_m_min, freezer_temp_c, estimated_giveaway_pct

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Custom Food Processing Line Orchestration with CrewAI Agents