DEV Community

Cover image for How a 5-Day AI Agents Intensive Course Helped Me Build FoodMate, A Multi Agent Food Concierge
Shiyaz Amal
Shiyaz Amal

Posted on

How a 5-Day AI Agents Intensive Course Helped Me Build FoodMate, A Multi Agent Food Concierge

#googleaichallenge #ai #agents #devchallenge

How a 5-Day AI Agents Intensive Course Helped Me Build FoodMate, A Multi Agent Food Concierge

When I signed up for the Google × Kaggle 5-Day AI Agents Intensive, I didn't expect to finish a polished project in a single week. But the course structure, hands-on codelabs, and community support gave me the confidence to build something simple, useful, and real: FoodMate, a multi-agent food recommendation assistant.

What I learned

The biggest idea that stuck with me was that agents are teams, not single models. Separating tasks into agents as preference, nutrition, verification, made the system easier to reason about, test, and extend. The course showed practical patterns:

  • Tool use & grounding (how to fetch external info safely)

  • Function calling and structured outputs (so downstream apps can use results)

  • Agent orchestration (agents communicating in sequence and in parallel)

Why FoodMate

Food is personal. In Sri Lanka, small constraints like time, budget, and local ingredients shape daily choices. I built FoodMate to propose quick, culturally relevant meal ideas, check a simple nutrition heuristic, and provide healthier swaps when appropriate. It’s practical, local focused, and intentionally tiny so it runs even with limited resources.

The build

  • Architecture: Preference Agent | Recipe Agent | Nutrition Agent | Aggregator

  • Tech: Kaggle Notebook, Python, Gemini / ADK patterns (with a fallback local recipe DB for quota issues)

  • Demo: Video walkthrough linked below

You can view the complete notebook and demo here:

What surprised me

Working through the codelabs made me realize agents don’t need to be exotic. Even small, reliable modules that do clear jobs create a system that feels “intelligent” and actually helpful. Also, the community support in the Kaggle Discord was huge. People helped debug codelabs and suggested better prompt designs.

If I had more time

I’d add user memory (to remember preferences), deploy the agent to Agent Engine or Cloud Run, and connect to local restaurant menus for live suggestions. I’d also build a simple mobile UI so people could use FoodMate while shopping.

Final thought

This intensive didn’t just teach me tools, it changed my mindset. I moved from “how do I query a model?” to “how do I design a small team of agents that reliably solves one useful problem?” That’s what I’ll be building next.

Kaggle notebook: https://www.kaggle.com/code/shiyazamal/capstone-foodmate-multi-agent-food-recommendati

Demo video: https://youtu.be/-3B8amyQBKc

If you'd like feedback on your project or want to collaborate, ping me here or on Kaggle: shiyazamal.

Top comments (0)