Skip to main content
Back to challenges
Challenge

Orchestrate Life-Sciences Park Feasibility Team with CrewAI

Evaluating complex life-science development projects requires cross-functional synthesis across market demand, specialized MEP engineering, and biotech zoning. Build a CrewAI agent team to collaborate on site selection reports and achieve an evaluation pass rate of 90% on benchmark cases.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Deploy a multi-agent CrewAI orchestration with specialized agent roles for market research, biotech zoning, and specialized MEP compliance.

Delivery guide

How work is evaluated

Evaluation

Evaluates multi-agent CrewAI output completeness and domain constraint validation.

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

Multi-Specialist Criteria Test

Verifies both zoning and MEP agent assertions are reflected in final decision.

Binary check

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

Dimension 2

Feasibility Accuracy

Correct classification of site suitability for biotech tenants. • target: 0.9 • 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

What you should walk away with

  • Define specialized CrewAI agents (Zoning Specialist, MEP Engineer, Life Science Market Analyst).

  • Design sequential and hierarchical tasks to create comprehensive site feasibility blueprints.

  • Implement agent memory and tool sharing for cross-domain validation.

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of international life science hub site properties, including structural floor loading ratings, vibration dampening specs, and HVAC air exchanges.

Challenge setup

Evaluates multi-agent CrewAI output completeness and domain constraint validation.

Challenge input

JSON with site_location, floor_load_capacity_psf, hvac_air_changes_per_hr, lab_biosafety_level

CrewAI

Assigned framework for role-playing multi-agent workflows.

Evaluated output

JSON with overall_viability, zoning_clearance, mep_readiness_score, key_recommendation

Evaluation checks
  • Verifies both zoning and MEP agent assertions are reflected in final decision.
  • Correct classification of site suitability for biotech tenants. • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: MultiAgent_Collaboration_Eval
  • Feasibility Accuracy target: 0.9
  • 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
  • Zed · Optional

Evaluation contract

  • Multi-Specialist Criteria Test · Weight 1
  • Feasibility Accuracy · Weight 1

Metrics

  • Feasibility Accuracy · Target 0.9

Benchmarks

  • MultiAgent_Collaboration_Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with site_location, floor_load_capacity_psf, hvac_air_changes_per_hr, lab_biosafety_level

    Output: JSON with overall_viability, zoning_clearance, mep_readiness_score, key_recommendation

    Execution harness: Python

Evaluation tools

  • CrewAI · Orchestration Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Orchestrate Life-Sciences Park Feasibility Team with CrewAI