Skip to main content
Back to challenges
Challenge

Cancer Organoid Quality Control Agent with CrewAI

NIH news highlights how human cancer models and patient-derived organoids accelerate precision therapy research. However, organoid culture pipelines are prone to batch effects, contamination, and cell viability degradation. In this challenge, developers will use CrewAI to orchestrate a team of specialized agents (Imaging QC Agent, Viability Analyst, and Batch Correction Agent) that process organoid assay images and dose-response data to detect experimental anomalies and recommend lab reruns.

Data ScienceHosted 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 a multi-agent laboratory quality control team using CrewAI to monitor patient-derived cancer models.

Delivery guide

How work is evaluated

Evaluation

Evaluates the QC crew's capability to flag invalid plate wells and recommend lab reruns.

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

fail_status_check

Verify low viability control results in FAIL status

Binary check

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

Dimension 2

qc_precision

Precision of invalid plate detection against ground truth QA benchmarks • target: 0.92 • 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

  • Design role-playing autonomous agent teams using CrewAI framework

  • Incorporate image metrics and dose-response curve parameters into agent tasks

  • Detect microplate edge effects and viability threshold violations in cell lines

  • Automate rerun recommendation logs for laboratory automation workflows

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic high-throughput organoid screen microplate metrics, IC50 drug sensitivity curves, and viability quality control scores.

Challenge setup

Evaluates the QC crew's capability to flag invalid plate wells and recommend lab reruns.

Challenge input

JSON containing plate_id, mean_viability_control, edge_effect_detected (bool)

CrewAI

Mandatory CrewAI framework

Evaluated output

JSON containing status (PASS/FAIL) and rerun_wells (list of strings)

Evaluation checks
  • Verify low viability control results in FAIL status
  • Precision of invalid plate detection against ground truth QA benchmarks • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: LabQC-Bench
  • Qc Precision target: 0.92
  • 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

  • fail_status_check · Weight 1
  • qc_precision · Weight 1

Metrics

  • qc_precision · Target 0.92

Benchmarks

  • LabQC-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing plate_id, mean_viability_control, edge_effect_detected (bool)

    Output: JSON containing status (PASS/FAIL) and rerun_wells (list of strings)

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Cancer Organoid Quality Control Agent with CrewAI