🍃 Olá, pessoal! Welcome to the 8th edition of the Global Data Science Challenge: Green Agents of Change 🍃

What’s this year’s mission, who’s our partner, how will we change the world, and why the Portuguese greeting? Simple: we’re a global community with global ambitions, and this year we’re teaming up with UNICEF to help young people drive climate action where it counts, through meaningful, sustainable careers.

Our focus: empowering youth across Brazil to explore, discover, and pursue green and future-proof jobs. The path from “I’m curious” to “I’m hired” can feel like a maze, so we’ll build an assistant that brings clarity. Whether someone knows exactly what they want or has no idea where to begin, your agent will help connect interests, skills, and values to real opportunities and training pathways.

Why sustainability? Because the effects of climate change are already shaping daily life. Guiding the next generation toward green careers isn’t just smart - it’s essential for resilient communities and a thriving planet.

Your challenge: collaborate with AI agents to sift through heaps of job descriptions and training opportunities across Brazil, match people to roles that fit their preferences and potential, and recommend concrete learning paths to get there. That means retrieval over real data (not just model memory), thoughtful matching and ranking, and smart prompt engineering.

This year we also partnered up with Mistral. Their LLM models will serve as brains for out AI agents 🤖

As always, the Global Data Science Challenge is about community as much as competition. Connect, share, learn, build, and have some fun along the way.

Ready, agents of change? Let’s turn climate ambition into careers!

Here's a breakdown of what you'll find in this repository:

• Notebooks: The tutorials folder contains a collection of five thoughtfully created tutorials. These tutorials serve as your expert guides, presenting you with step-by-step instructions and insights into potential solutions. Delve into data exploration, feature engineering, and model building, as these Jupyter notebooks provide a solid foundation for understanding the problem at hand and developing effective strategies.

• Udemy:

  • Complete Guide to MCP in Python
  • Intro to MCP

• Coursera:

  • Building AI Agents with MCP Servers
  • Introduction to LangChain Framework
  • Using LangChain with Amazon Bedrock

• AWS:

  • You can access (skill builder website) and log in with your Capgemini account. If you don't have one, follow the steps on the page to create one.
  • Building Production-Ready AI Agents with Amazon Bedrock AgentCore

• Mistral:

  • Building MCP powered Assistants
  • Mistral Cookbook