Back to Catalog

Hands-On Multi-Agent AI: Meal & Grocery Planner with CrewAI

IntermediateGuided Project

Master CrewAI-based multi-agent workflows with Pydantic, YAML-defined agents, and CrewBase. Learn hands-on AI task orchestration through a real-world scenario involving recipe planning, shopping list generation, and budget advising. Leverage IBM Granite LLM and the Serper web tool, showcasing agent coordination, structured data modeling, and YAML configuration. Explore how CrewAI workflows bridge LLMs with real-world planning tasks, automation, and multi-agent collaboration.

Language

  • English

Topic

  • Skills Network

Skills You Will Learn

  • Generative AI, CrewAI, LLM, AI Agent, Agentic AI, Multi Agent

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 45 minutes

Platform

  • SkillsNetwork

Last Update

  • August 20, 2025
About this Guided Project
AI agents are reshaping how we automate everyday workflows, from customer support to supply chain planning. But to move beyond simple prompts and chatbots, you need to know how to structure tasks, coordinate agents, and deliver reliable outputs. This guided project dives into CrewAI, a powerful framework for multi-agent orchestration, and teaches you how to build real-world, structured AI workflows using Pydantic, YAML, and CrewBase.

Through hands-on implementation, you'll build a complete Meal and Grocery Planner AI system. Unlike single-agent LLM prompts, this system coordinates multiple agents to simulate realistic planning tasks—researching recipes, generating shopping lists, offering budget tips, and managing leftovers—all while respecting constraints like dietary needs and cost limits.

You'll use IBM Granite LLM, Serper web search, and CrewAI tooling to define agents, tasks, and structured outputs in both code and YAML. The project showcases how Pydantic models enforce consistent formats, how YAML can declaratively define agent behavior, and how CrewBase integrates everything for production-quality orchestration. By the end of this project, you’ll have built a real, working AI workflow with applicability in any domain requiring structured task management.

What You'll Learn

After completing this project, you will be able to:
  • Build a fully functional CrewAI workflow to automate a multi-agent task
  • Use Pydantic models to enforce structured outputs from LLMs
  • Define agents and tasks using YAML, and integrate them using CrewBase
  • Leverage LLMs like IBM Granite and web tools like Serper for real-time data-driven decision making
  • Coordinate reasoning across multiple AI agents to simulate planning, execution, and summarization

Who Should Enroll

This project is perfect for:
  • Developers exploring agentic AI systems and real-world orchestration use cases
  • AI/ML practitioners looking to implement structured outputs and task delegation
  • Software engineers who want to learn YAML-based configuration in AI workflows with CrewAI
  • Technical professionals interested in multi-agent collaboration using LLMs

What You'll Need

Before beginning this guided project, you should have:
  • A basic understanding of Python
  • Familiarity with foundational AI/LLM concepts (prompting, tasks, structured data)
  • A modern web browser such as Chrome, Firefox, Safari, or Edge

Instructors

Karan Goswami

Data Scientist at IBM

I am a dedicated Data Scientist and an AI enthusiast, currently working at IBM's Skills Builder Network. Learning how some simple mathematical operations could be used to make predictions and discover patterns sparked my curiosity, leading me to explore the exciting world of AI. Over the years, I’ve gained hands-on experience in building scalable AI solutions, fine-tuning models, and extracting meaningful insights from complex datasets. I'm driven by a desire to apply these skills to solve real-world problems and make a meaningful impact through AI.

Read more

Contributors

Joseph Santarcangelo

Senior Data Scientist at IBM

Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.

Read more

Jigisha Barbhaya

Data Scientist

I am a Data scientist at IBM and Lead instructor at Skills network. I love to learn and educate. I have completed my MSc(Computer Application) specialisation in Data science from Symbiosis University.

Read more

Tenzin Migmar

Data Scientist

Hi, I'm Tenzin. I'm a data scientist intern at IBM interested in applying machine learning to solve difficult problems. Prior to joining IBM, I worked as a research assistant on projects exploring perspectivism and personalization within large language models. In my free time, I enjoy recreational programming and learning to cook new recipes.

Read more