Offered By: IBMSkillsNetwork
Hands-On Multi-Agent AI: Meal & Grocery Planner with CrewAI
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.
Continue readingGuided Project
Skills Network
At a Glance
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.
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
- 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
- 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
- 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
Estimated Effort
45 Minutes
Level
Intermediate
Skills You Will Learn
Agentic AI, AI Agent, CrewAI, Generative AI, LLM, Multi Agent
Language
English
Course Code
GPXX0NL4EN