Google ADK Plugins Explained | Logging, Guardrails, and Global Runtime Control
Google ADK Plugins let you add global runtime behavior across your AI agent system, including logging, guardrails, caching, error recovery, observability, and policy enforcement. In this walkthrough, we build a clear mental model for how Plugins work in Google ADK, how they differ from Callbacks, where they attach in the ADK execution lifecycle, and how they can observe, modify, or intercept model and tool execution. We also cover the main plugin callback hooks, built-in plugin patterns from the official documentation, and why Plugins are such an important building block for secure, scalable, production-ready agent workflows. 📘 What we covered • What Plugins are in Google ADK • Why Plugins matter in multi-agent systems • Plugins vs Callbacks • How Plugins attach to the Runner • Global runtime behavior vs local agent customization • Plugin callback hooks across the ADK lifecycle • Built-in plugin examples like Reflect and Retry, Context Filter, and BigQuery Analytics 🎥 Previous videos → Video 1: Build Your First AI Agent with Google ADK → • Build Your First AI Agent with Google ADK ... → Video 2: Function Tools in Google ADK (Finance Assistant) → • Function Tools in Google ADK | Build a Fin... → Video 3: OpenAPI Tools in Google ADK (Chuck Norris API) → • OpenAPI Tools in Google ADK | Connect Your... → Video 4: Sequential Agents in Google ADK (Podcast Transcript Assistant) → • Sequential Agents in Google ADK | Podcast ... → Video 5: Parallel Agents in Google ADK (Multi-Agent Travel Planner) → • Parallel Agents in Google ADK | Multi-Agen... → Video 6: Loop Agents in Google ADK → • Loop Agents in Google ADK | Critic-Refiner... → Video 7: Callbacks in Google ADK → • Callbacks in Google ADK | Observe, Customi... → Video 8: How Google ADK Agents Run → • How Google ADK Agents Run | Event Loop Exp... → Video 9: Events in Google ADK → • Events in Google ADK | Debug Tool Calls, T... → Video 10: Context Management in Google ADK → • Context Management in Google ADK | Session... → Video 11: Evaluating AI Agents in Google ADK | High-Level Overview → • Evaluating AI Agents in Google ADK | High-... → Video 12: Evaluating AI Agents in Google ADK | Hands-On Demo → • Evaluating AI Agents in Google ADK | Hands... → Video 13: Google ADK Artifacts Explained | High-Level Overview → • Google ADK Artifacts Explained | Save, Ver... 📺 Playlists → Building AI Agent with Google ADK Playlist → • Building AI Agents with Google ADK → Function calling Playlist → • Function Calling with LLMs #adk #googleadk #aiagents #genai #llm #plugins #guardrails #observability #aideveloper

Google ADK Plugins Demo | Logging and Guardrails

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI

Is RAG Still Needed? Choosing the Best Approach for LLMs

Build you first AI agent in 60 mins - Claude Code Hands-on Part 1

Why Aliens Would NEVER Invade Africa

Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems

How To Think SO CLEARLY People Assume You're A Genius

OWASP's Top 10 Ways to Attack LLMs: AI Vulnerabilities Exposed

How to use Sessions & State in Google ADK - Google Agent Development Kit for Beginners (Part 5)

Context Management in Google ADK | Session vs State vs Memory

Stop Prompting Claude. Use Karpathy's Method Instead.

What It Actually Takes to Deploy a Voice Agent to a Fortune 500

A2A vs MCP: AI Agent Communication Explained

How RAG, GraphRAG, and Context Engineering Improve AI Performance

God Says:"TAKE THIS MESSAGE SERIOUSLY, BECAUSE ONLY YOU ARE SEEING IT"/God Message Now/God Message

Hermes Architecture EXPLAINED: Memory, Context & Gateways

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

What is an Agent Harness? and How to build a great one!

