Skip to main content
Loading navigation
Back to challenges

CrewAI Autonomous Quick Commerce Demand & Stock Routing Crew

Rapid QSR and quick-commerce chains need dynamic stock rebalancing across dark stores during peak hours. Build a role-playing agent swarm using CrewAI where Inventory, Logistics, and Pricing agents collaborate to eliminate out-of-stock events.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Build a collaborative inventory management crew using CrewAI agents assigned distinct operational roles.

How work is evaluated

Evaluation

Evaluates stock rebalancing decision quality and SLA protection.

Datasets

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

How submissions are scored

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

transfer_quantity_valid

Checks if transferred amount satisfies surge without depleting source.

Binary check

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

Dimension 2

sla_protection_rate

Percentage of dynamic demand satisfied • target: 0.95 • range: 0-1

Binary check

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

Learning goals

  • Define CrewAI agents with clear roles, goals, and backstory configurations

  • Implement sequential and hierarchical task execution strategies in CrewAI

  • Optimize local dark store stock reallocation based on real-time order surges

Resources

Dataset notes

Hourly sales velocity and dark store stock levels across metro hubs.

Challenge setup

Evaluates stock rebalancing decision quality and SLA protection.

Challenge input

JSON store inventory state

CrewAI

Mandatory framework requirement

Evaluated output

JSON stock transfer execution order

Evaluation checks
  • Checks if transferred amount satisfies surge without depleting source.
  • Percentage of dynamic demand satisfied • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: SupplyChain-Bench
  • Sla Protection Rate target: 95%
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional
Observation
  • Galileo · Optional
Reward / Eval
  • Galileo · Optional

Evaluation contract

  • transfer_quantity_valid · Weight 1
  • sla_protection_rate · Weight 1

Metrics

  • sla_protection_rate · Target 0.95

Benchmarks

  • SupplyChain-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON store inventory state

    Output: JSON stock transfer execution order

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about CrewAI Autonomous Quick Commerce Demand & Stock Routing Crew