Demystifying AI Agents at GDG Hamburg DevFest 2025

I recently had the opportunity to speak at GDG Hamburg DevFest 2025, where I broke down what AI agents actually are and how to build them effectively. If you missed it, you can catch the full recording here: Demystifying Agents - GDG Hamburg DevFest 2025.

Here are the core takeaways from the session:

Defining Agents

At their core, intelligent agents plan, take steps, retrieve data, interact with their environment (via tool calls), and remember context.

The Problem with "Mega Agents"

Giving a single Large Language Model too much information and responsibility often causes it to lose focus and fail at specific tasks.

The Multi-Agent Solution

Instead of one massive agent, it's better to build a system of focused experts. I demonstrated a real-world plumbing business workflow where an Orchestrator Agent coordinates a Field Service Agent and an Office Agent. This multi-agent setup successfully reduced a frustrating 40-minute manual communication loop down to just 40 seconds.

The Tech Stack

• Models: You don't always need massive pro models. Highly capable models like Gemini 2.5 Flash are perfect for focused domain experts.
• Python: Python's automatic function calling makes passing context and setting up tool calls practically seamless.
• Google Agent Development Kit (ADK): Building agents from scratch makes testing and debugging a nightmare. Using a framework like the ADK gives you complete UI visibility into inter-agent communication, execution timings, and tool payloads out of the box.

The Takeaway

Building multi-agent systems is incredibly powerful when you let humans focus on the emotional tasks (like client negotiation) and let specialized agents handle the data routing.

Feel free to check out the video above, and you can find the sample code for the WhatsApp-integrated multi-agent system on my GitHub!