Skip to main content
Back to Prompt Library
implementation

Setup CrewAI Team with Modal Deployment

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: CrewAI Tumor Mutant Dosage Modeling on Modal Serverless

Format
Code-aware
Lines
13
Sections
4
Linked challenge
CrewAI Tumor Mutant Dosage Modeling on Modal Serverless

Prompt source

Original prompt text with formatting preserved for inspection.

13 lines
4 sections
No variables
0 checklist items
import modal
from crewai import Agent, Task, Crew, Process

app = modal.App('cancer-genomics-crew')

@app.function()
def run_genomics_crew(cohort_data_json: str):
    analyst = Agent(
        role='Genomics Data Analyst',
        goal='Calculate mutant dosage metrics across 60k sample profiles',
        backstory='Expert computational biologist specializing in tumor clonality.',
        verbose=True
    )
    
    # Define tasks and execute crew
    return {'status': 'completed'}

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.