For Small Business · v3.0

The AI course that actually ships.

Eleven modules from the language-model basics to a shipped, production capstone. Built for small-business owners and operators — assumes zero prior AI experience. Interactive playgrounds, quizzes, and three capstone tracks you can pick from. Real examples across agencies, retail, real estate, professional services, and content businesses. No hype.

11
Modules · roughly 5½ hours end to end
40+
Quiz questions · check yourself after each module
3
Live interactives · playground, agent trace, ⌘K search
Start here

Where should you begin?

Five quick questions and I'll route you to the right module. Nothing is graded and you can always take the long path.

Curriculum

Eleven modules, foundations first.

Modules 1–4 are concepts, 5–7 are patterns, 8–10 are hands-on builds, 11 is the capstone project. Mark modules complete as you go — the tracker follows you across sessions.

01

What AI actually is (and isn't)

Language models, tokens, context, temperature, and why 'talking to AI' works. Set the mental model you'll use for the rest of the course.

Foundations · 15 min
02

Prompting like a professional

Structure, role, examples, guardrails. The prompt patterns that outperform 'be more specific' every time.

Foundations · 20 min
03

Tools, connectors, and the outside world

How a language model becomes an app. Function calling, browser use, connectors — and where Perplexity Computer fits in.

Capabilities · 20 min
04

What is an agent, really?

Workflows vs agents. The six canonical agent patterns from Anthropic, illustrated with agency examples you can run tomorrow.

Core concept · 25 min
05

Flows: chaining steps that don't need a brain

When determinism beats intelligence. Build an inbound-lead intake flow in n8n and a Cloudflare Worker version alongside it.

Automation · 25 min
06

Giving AI your own knowledge (RAG)

Retrieval-augmented generation for your business. Embed your past proposals, quotes, or docs; get grounded, cited answers.

Data · 30 min
07

MCP: the USB-C of AI

The Model Context Protocol lets any agent plug into any tool. Install one, use it in Claude / Computer / Cursor.

Interop · 20 min
08

Build your first agent in Perplexity Computer

Skills, subagents, cron, connectors. Stand up a weekly lead-research agent that runs while you sleep.

Hands-on · 40 min
09

Build an agent with the OpenAI & Anthropic APIs

Copy-paste JavaScript for a working agent that uses tools, retries on failure, and returns structured JSON.

Hands-on · 45 min
10

From prototype to production

Costs, evals, guardrails, PII, and the questions to ask before any AI touches a client. A pragmatic ship-checklist.

Ship it · 30 min
11

Capstone: pick a track and ship it

Three ship-ready tracks: Proposal Assistant, Content Ops Engine, or Support Copilot. Pick the one that saves you the most time, then build the smallest useful version this week.

Capstone · 60 min
How to use this course

Learn by doing, one module at a time.

1. Read the concept

Every module starts with plain-language explanation and a diagram. No jargon without definitions — hover any underlined term to see it defined.

2. Play with it live

Modules 2 and 9 have live playgrounds. Test prompts against real APIs or watch an agent's tool-calling loop run in real time.

3. Take the quiz

Each module ends with 3–5 questions. Pass with 70% and the module marks itself complete. Retry anytime.

4. Do the exercise

Every module ships with a downloadable starter file — an actual prompt, workflow, or code file you can use tomorrow.

Reference

A pocket glossary.

The vocabulary of AI, in plain language. Every term here is also hoverable inline inside the modules — no need to memorize.

TermMeaning
LLMLarge language model. The prediction engine at the core of every AI product.
TokenRoughly ¾ of a word. Models charge per token.
Context windowHow many tokens the model can hold at once. Its short-term memory.
PromptThe input text you send. Includes system instructions + user message + prior conversation.
System promptThe always-on instruction at the top of every conversation. Sets role, tone, rules.
Tool / function callingLetting the model call a function you defined (weather, search, send-email).
ConnectorA pre-built package of tools for a popular app (Gmail, Notion, Slack).
WorkflowA predefined sequence of steps involving LLMs. You draw the flowchart.
AgentA system where the model picks its own steps and tools to reach a goal.
RAGRetrieval-augmented generation. Look up relevant chunks first, then ask the model.
EmbeddingA vector that represents the meaning of a chunk of text.
Vector databaseA DB optimized for finding similar embeddings quickly.
MCPModel Context Protocol. Open standard so any tool plugs into any AI app.
EvalA test suite of inputs + expected outputs to measure model quality.
GuardrailA rule that prevents an agent from doing something dangerous.