05 — Agents

What Are Agents

AI agents are LLM-powered systems that can perceive their environment, reason about goals, and take actions using tools — going beyond single-turn chat to autonomous, multi-step task completion.

Covered Frameworks

Framework	Folder	Best For
GCP Agent Development Kit	GCP-ADK/	Google Cloud-native agents
LangChain	LangChain/	General-purpose agent chains
LangGraph	LangGraph/	Stateful, graph-based agents
CrewAI	CrewAI/	Role-based multi-agent crews

Recommended Learning Path

1. Read Agent Fundamentals — understand what agents are
2. Study Agent Patterns — learn common design patterns
3. Pick one framework and work through its Fundamentals → Simple → Complex files
4. Return to Interview Q&A to consolidate knowledge

Framework Comparison

Dimension	GCP ADK	LangChain	LangGraph	CrewAI
State management	Session-based	Memory modules	Graph state	Shared crew context
Multi-agent	Via orchestration	Via chains	Via graph nodes	Native (Crew)
Cloud integration	GCP native	Cloud-agnostic	Cloud-agnostic	Cloud-agnostic
Best complexity	Medium-High	Low-Medium	Medium-High	Medium-High

Code Labs

Section	What You'll Build	Link
Agent Types	Simple → Intermediate → Complex agents across all 4 frameworks	CodeLabs — Agent Types
Architecture Patterns	7 multi-agent coordination patterns × 4 frameworks	CodeLabs — Architecture Patterns

Notes

• 01 — Agent Fundamentals
• 02 — Agent Patterns
• 03 — Interview Q&A

Resources

• Building Applications with AI Agents

Navigation

Previous: 04 — MCP | Next: 06 — Agentic AI