Contents

Agents

Overview

View as:

05 - AI Agents

What Are AI 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.


What You'll Learn

#ConceptDescription
01What Are AI AgentsDefinition, the four pillars, and the autonomy spectrum
02Anatomy of an AI AgentDeep dive into the six core components: Brain, Planning, Tools, Memory, Perception, and Governance
03Agent MemoryThe four memory types, the memory lifecycle, and how agent memory differs from workflow memory
04AI Agent CapabilitiesPerception, reasoning, planning, memory, tool use, and self-correction
05AI Agent Use CasesWhen to use AI Agents; domain-specific examples and decision framework
06Enterprise vs Personal AI AgentsProduction requirements, security, governance, and framework selection
07Agent Evaluation BasicsSingle-agent test sets, tool-call and output checks, lightweight LLM-as-judge, when to graduate to system-level eval

Hands-On Labs

Build AI Agents using four major frameworks, progressing from simple to complex:

FrameworkBest ForLabs
GCP Agent Development KitGoogle Cloud-native AI AgentsFundamentals → Simple → Complex
LangChainGeneral-purpose AI Agent chainsFundamentals → Simple → Complex
LangGraphStateful, graph-based AI AgentsFundamentals → Simple → Complex
CrewAIRole-based multi-AI-Agent crewsFundamentals → Simple → Complex

See AI Agent Types for a complexity progression overview across all four frameworks.


Framework Comparison

DimensionGCP ADKLangChainLangGraphCrewAI
State managementSession-basedMemory modulesGraph stateShared crew context
Multi-AI-AgentVia orchestrationVia chainsVia graph nodesNative (Crew)
Cloud integrationGCP nativeCloud-agnosticCloud-agnosticCloud-agnostic
Best complexityMedium–HighLow–MediumMedium–HighMedium–High

  1. What Are AI Agents - understand the definition and core pillars
  2. Anatomy of an AI Agent - understand the six core components in depth
  3. Agent Memory - dive deep into how agents remember and learn over time
  4. AI Agent Capabilities - learn what makes an AI Agent capable
  5. AI Agent Use Cases - understand where AI Agents add the most value
  6. Enterprise vs Personal AI Agents - understand production constraints
  7. Agent Evaluation Basics - learn to test and evaluate a single agent before scaling up
  8. Pick one framework and work through its Fundamentals → Simple AI Agent → Complex AI Agent labs
  9. Return to Interview Q&A to consolidate knowledge

Resources


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

AI-assisted content - always verify, always explore multiple perspectives·