My Journey Learning Google ADK: Building AI Agents from Scratch | Part 5
Last Updated on February 6, 2026 by Editorial Team
Author(s): Pranav Dhopey
Originally published on Towards AI.
Building AI Agents from Scratch | Part 5
Bonus part! If you’re following along, you’ve already mastered Part 1 (Basics), Part 2 (State), Part 3 (Workflows), and Part 4 (Multi-Agent Routing).
AgentTool to wrap agents as callable tools (unlike sub_agents where control transfers). The main agent stays in control, calls specialists, and gets results back. Great for orchestration.This article explores the concept of AgentTool, a feature that enables orchestration by allowing a main agent to control specialist agents without transferring control completely. It emphasizes the real-world application of building a DevOps Copilot, showcasing how to generate commands and handle errors effectively through specialist agents that return structured data. The piece also discusses when to use AgentTool versus sub-agents, providing a framework for selecting the appropriate method for managing tasks while integrating practical examples to demonstrate the operation of these tools in a coherent system.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
