← All Programs
Technology

AI & Automation — Private Tutor Track

A complete beginner-to-pro curriculum teaching students to understand, build, and deploy AI and automation systems. Self-paced study guide with hands-on labs.

⏱ Self-paced · ~120 hours
🚀 The fastest way to learn AI: read a lesson, do the lab, then ask the tutor to check your work.
1

Module 1 · AI Foundations

Beginner
Beginner

What is Artificial Intelligence?

🎯 Objective: Explain AI vs ML vs DL; identify real-world AI.

Artificial Intelligence is the field of making machines perform tasks that need human intelligence. Machine Learning (ML) is a subset where systems learn patterns from data. Deep Learning uses neural networks with many layers. We meet AI daily in spam filters, recommendations, and voice assistants. Key idea: AI is a tool, not magic — it is only as good as its data and the problem framing.

🧪 Lab: List 5 AI tools you use weekly and classify each as ML or rule-based.
Self-check: Give one example where a rule-based system beats ML, and one where ML is essential.
Beginner

How Machines Learn (Data, Models, Training)

🎯 Objective: Describe the supervised learning loop.

A model is trained on labelled examples: it adjusts internal parameters to minimize error. Training = optimization (gradient descent). Inference = using the trained model on new data. Key terms: features (inputs), labels (targets), loss function, epoch, overfitting (memorizing instead of generalizing). The golden rule: never test on your training data.

🧪 Lab: Use a no-code tool (Teachable Machine) to train a simple classifier.
Self-check: Why is a 100% accurate model on training data still suspicious?
2

Module 2 · Prompt Engineering & LLMs

Beginner
Beginner

Talking to LLMs Effectively

🎯 Objective: Write zero-shot, few-shot, and role prompts.

Large Language Models respond to well-structured prompts. Core techniques: clear instruction, context, examples (few-shot), role assignment ('You are a tutor...'), and chain-of-thought ('think step by step'). Always specify the output format (JSON, bullet list, tone). Small prompt changes can swing results dramatically — prompt engineering is the new literacy.

🧪 Lab: Write 3 prompts that extract structured JSON from messy text.
Self-check: When would few-shot prompting beat a long instruction?
Beginner

Building with the LLM API

🎯 Objective: Call an LLM via code safely.

Use the chat-completions pattern: system message (sets role/rules) + user message (the ask), with temperature (creativity) and max_tokens (length) controls. Keep API keys secret (environment variables, never in code). Batch requests with rate-limit handling. Prefer local/free models (Ollama) to avoid per-call cost at scale.

🧪 Lab: Run llama3.2 locally via Ollama and call it from Python.
Self-check: Why should temperature be near 0 for a math tutor but higher for a brainstorming bot?
3

Module 3 · Automation Fundamentals

Intermediate
Intermediate

Workflow Automation Concepts

🎯 Objective: Map a manual process to an automated one.

Automation = trigger + action + conditions. First document the manual flow (inputs, steps, outputs, exceptions), then pick a tool: n8n/Make/Zapier for no-code, or Python for full control. Always build for failure: what happens when a step errors? The best automations have clear logging and a human fallback.

🧪 Lab: Draw an automation map for 'save email attachments to cloud + notify me'.
Self-check: Name three manual tasks in your study life you could automate this week.
Intermediate

Connecting APIs & Webhooks

🎯 Objective: Use REST APIs and webhooks.

REST = request/response over HTTP (GET reads, POST creates). Webhooks = a server pushes events to your URL when something happens. Authenticate with API keys or OAuth. Parse JSON. Handle errors with retries and exponential backoff. Rate limits are real — respect them or get blocked.

🧪 Lab: Create a webhook receiver that logs incoming JSON.
Self-check: What is the difference between polling an API and receiving a webhook?
4

Module 4 · Building AI Agents

Advanced
Advanced

Agent Architecture (Tools, Memory, Planning)

🎯 Objective: Design a tool-using agent loop.

An agent = LLM + tools + memory. The loop: perceive -> think -> act (call a tool) -> observe -> repeat until done. Give the model functions it can call (search, calculator, your API). Keep a conversation memory for context. Guard every tool call with input validation — an agent that can send email must be constrained.

🧪 Lab: Build a CLI agent that can call a calculator tool via function-calling.
Self-check: What could go wrong if an agent has unrestricted access to send messages?
Advanced

Retrieval-Augmented Generation (RAG)

🎯 Objective: Build a RAG pipeline over your docs.

RAG = retrieve relevant chunks, then generate with that context. Steps: chunk documents, embed them, store in a vector database, query by similarity, rerank, then prompt the LLM with the retrieved text. This keeps answers grounded in YOUR data and current — no hallucination about facts you provided.

🧪 Lab: Index this site's study guides and ask the agent a program question.
Self-check: Why does chunk size matter in a RAG system?
5

Module 5 · Deployment & MLOps

Professional
Professional

Shipping to Production

🎯 Objective: Containerize and serve an AI app.

Package with Docker, expose via an API (FastAPI), add a reverse proxy (Caddy/Nginx) with TLS. Monitor latency and errors. Use systemd timers for scheduled jobs. Keep secrets out of code (env vars / secret managers). A working demo behind HTTPS beats a perfect notebook on localhost.

🧪 Lab: Dockerize the chatbot API and serve it behind Caddy with HTTPS.
Self-check: Why is 'it works on my machine' not good enough for production?
Professional

Observability, Cost & Safety

🎯 Objective: Run AI safely and cheaply.

Log every call, cap token spend, cache repeated responses, and prefer local models for high-volume tasks. Add guardrails: input validation, output filtering, and human-in-the-loop for risky actions. Audit monthly. The cheapest token is the one you didn't need to send.

🧪 Lab: Add a rate limiter + cost estimator to your chatbot.
Self-check: List three guardrails you would add before letting an agent act on a real bank account.
CLIAI Tutor
Hi! I'm your CLIAI tutor. Ask me about any CLI College program, lesson, or AI topic. 📚