planning

CrewAI Agent & Task Definition

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

Linked challenge: Develop a Low-Resource Language Data Generation Crew

Format

Text-first

Lines

Sections

Linked challenge

Develop a Low-Resource Language Data Generation Crew

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Define the roles, goals, and tools for your CrewAI agents. Create at least three agents: a 'Data Generator' (using Gemini 2.5 Pro), a 'Linguistic Validator' (using OpenAI o3 for cross-lingual checks), and a 'Cultural Reviewer'. Detail their tasks and how they will interact.

Adaptation plan

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

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

planning

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Develop a Low-Resource Language Data Generation Crew

Challenge of building LLMs for low-resource languages, this challenge focuses on creating an intelligent agent crew to significantly accelerate and enhance the creation of high-quality, culturally-relevant datasets. The lack of robust training data is a major hurdle for these languages, and traditional methods are slow and costly. Your task is to build a multi-agent system that collaborates to generate synthetic text, translate, and perform linguistic and cultural validation for a specified low-resource language. The system will employ Gemini 3 for advanced generative capabilities and cross-lingual understanding, alongside specialized agents for validation. Crucially, the agents will communicate via an A2A Protocol, ensuring efficient hand-offs and feedback loops, with human-in-the-loop checkpoints for final verification.

Open challenge

Related prompts

Browse library

A2A Communication Protocol Design

planning

Implement Data Generation Workflow with DSPy

implementation

Human-in-the-Loop Integration

implementation