Level 1.5 · AI Agents, Simplified

How AI Agents
Really Work

You've met AI and learned to prompt it. Before you build agents by hand (Level 2), get the mental model — the whole picture, trimmed to the parts that matter, in plain English.

🧭
How to use this: Ten stations, in order. Each numbered card is a big agent idea — tap it to open a deep dive. The chips below are the specific skills inside. You don't need to master everything — just build the mental model.

You are on Level 1.5 · Agents.

Start here — you already know the AI basics
1

What Is an AI Agent?

An AI that doesn't just chat — it pursues a goal.

Agent vs chatbotacts vs just talks What's a tool?an ability it can use Real use casesassistants, coding, data
Open deep dive →
2

The Engine Underneath

The LLM essentials every agent runs on.

Tokens & contextwhat it reads at once Temperature & controlstuning the output Open vs closedrun-your-own vs API Embeddingsmeaning as numbers
Open deep dive →
3

The Agent Loop

The cycle at the heart of every agent.

Perceiveread the input Reason & plandecide next step Actcall a tool Observe & reflectcheck the result
Open deep dive →
4

Tools & Actions

The abilities that let an agent do things.

What's a tool?a function it can call Tool definitionname, inputs, outputs Examplessearch, code, APIs, files
Open deep dive →
5

Prompting Your Agent

The instructions that steer good behavior.

Be specificsay exactly what you want Give examplesshow, don't just tell Iterate & testrefine the prompt
Open deep dive →
6

Agent Memory

How an agent remembers across steps and sessions.

Short vs long termnow vs forever Vector DBsearchable memory Summarize & forgetkeep it small
Open deep dive →
7

Agent Architectures

Proven patterns for how an agent thinks.

ReActreason + act Chain of Thoughtthink step by step MCPa standard plug for tools Multi-agenta team of agents
Open deep dive →
8

Building Agents

Three ways: by hand, function calling, or a framework.

From scratchyour own loop Function callingOpenAI · Gemini · Claude FrameworksLangChain · CrewAI · LangGraph
Open deep dive →
9

Testing & Watching Your Agent

Know if it works — and see what it's doing.

Metrics & teststools + whole flows Human in the loopa person checks Tracing & logssee every step
Open deep dive →
10

Agent Safety & Ethics

Keeping agents that act from doing harm.

Prompt injectiontricking the agent Sandboxing toolslimit what it can do Privacy & guardrailsPII, bias, red-teaming
Open deep dive →
🏆 You get how agents work — now go build them