Practical AI Class Outline

Practical AI: Using ChatGPT, Claude and Gemini Safely and Well

• Length: 90 minutes
• Format: small-group workshop, run as a conversation around one table
• Level: beginner, no prior AI experience needed
• Student handout: see Take-Home Card in this chapter
• Last revised: October 2026. AI apps change fast; check the settings menus and plan names the day before you teach (see Instructor notes).

The class uses the "brilliant intern" analogy and a short checklist for asking well (R.O.L.E.S.). It covers privacy and security early, and shows what AI apps can do now: search, see, listen and carry out tasks.

Know the room

• Run it as a conversation, not a lecture. With a small group, stop for questions anywhere.
• Welcome skeptics. If someone is wary of AI, treat that as an asset. Their concerns are often legitimate and the class should say so plainly. Invite them to be the "red team" during demos: their job is to catch the AI being wrong.
• Use the opening round to learn each person's experience level and goals.
• Nobody connects a personal email, calendar or drive account during class. Connected-account features are instructor demos only.

Class flow at a glance

Time	Section	Length
0:00	Welcome: what you want from AI, what worries you	10 min
0:10	How AI actually works: tools, tokens, reasoning	14 min
0:24	Privacy and security first	20 min
0:44	Hands-on: asking well, and managing a conversation	20 min
1:04	Demo tour: what AI can do now	16 min
1:20	Verification habits, handout, Q&A	10 min

Section 1: Welcome (10 min)

Opening round

Go around the table. Each person answers two questions:

1. "What is one thing in your life or work you would like help with?" (a letter, a project plan, learning a skill, fixing something)
2. "What worries you about AI, if anything?"

Write both lists on the whiteboard and leave them up all class. The first list becomes demo material in Sections 4 and 5. The second is a checklist: before the class ends, every worry on it should be addressed or honestly acknowledged.

Set expectations

• This class is neither cheerleading nor fear. It is like learning a new power tool: what it is good for, where it bites, and which guards to use.
• Skepticism is welcome. Several of today's habits exist because the skeptics are right about some things.
• Goal: leave with your privacy settings checked and three habits you can use tonight.

Section 2: How AI actually works (14 min)

The brilliant intern

"Think of AI as the smartest intern you have ever met. They have read nearly everything, they are fast, and they never get tired. But they are still an intern. They need clear instructions, they will confidently hand you wrong information if you do not check their work, and they badly want to give you an answer even when 'I'm not sure' would be better. Your job is to be a good manager."

Next-word prediction, briefly

These tools generate text by predicting what is most likely to come next, based on patterns in an enormous amount of writing. That is why the same tool can write a lovely thank-you note and also invent a book that does not exist. Both are "plausible next words."

The intern got tools

A year or two ago, the honest summary was "AI can talk, but it can't do anything." That is no longer true. The major apps can now:

• Search the web and show sources, often automatically.
• See: read a photo, a screenshot, a PDF or a live camera view.
• Listen and talk: hold a spoken conversation (voice mode).
• Run calculations and create files: spreadsheets, documents, charts.
• Do multi-step research: read dozens of pages and write a cited report (often called "Research" or "Deep Research").
• Carry out tasks (agents): click through websites, fill in forms, work with files on your computer, connect to email or a calendar.

Key point: more capability means more to manage. An intern who can only talk can only give you bad advice. An intern with your house keys can do real damage. That is why the next section is about security.

Tokens and context (3 min)

"AI doesn't read words, it reads chunks called tokens, roughly three quarters of a word each. Everything you type, everything you upload, and everything it writes back uses tokens. Think of the conversation as a whiteboard of fixed size: once it fills up, the oldest material gets erased."

Why this matters to a regular user:

1. Usage limits. "You've reached your limit, try again at 3 PM" is measured in tokens. Long chats and big uploads use up the allowance faster. Paid plans mostly buy more allowance.
2. Long conversations degrade. When the whiteboard is full, the AI forgets early details. (Section 4 covers what to do.)
3. Odd failures. Because it reads chunks rather than letters, it can miscount the letters in a word. A good reminder that it is not magic.

If someone asks "Does it cost me per message?": "Not in the regular apps. You get a usage allowance, not a meter. Per-token billing applies to developers using the paid API."

How AI "reasons" (4 min)

"If I ask you 17 times 24, you probably can't just blurt out the answer. You work it out on scratch paper. Older AI had to blurt: it predicted the answer one word at a time with no scratch paper. Newer 'thinking' or 'reasoning' models get scratch paper. Before answering, they write out steps for themselves: break the problem down, try an approach, check it, back up if it doesn't work. Then they write the answer."

What it looks like in the apps:

• A "Thinking..." indicator, often with a "Show thinking" panel you can open and read.
• Sometimes a choice in the model menu or a toggle ("Thinking", "Extended thinking", "Deep Think"); many apps now decide on their own how much to think.
• For math and data, the AI often writes and runs a small calculation behind the scenes instead of doing arithmetic "in its head." That is why "AI is bad at math" was mostly true of older chatbots.

When it helps: multi-step problems such as math, cut lists and material estimates, planning a schedule, troubleshooting with several possible causes, comparing options against several requirements.

When it doesn't matter: quick, simple tasks (rewording an email, a definition). Thinking makes answers slower and uses more of your allowance; the scratch paper is made of tokens too.

The honest caveats (good for the skeptic):

1. It is still prediction. The "thinking" is more predicted text, organized into steps. A useful technique, not a mind.
2. It can reason its way to a wrong answer, confidently, with neat-looking steps. Well-organized work is not the same as correct work.
3. The shown thinking is not a perfect window. Researchers have found the written-out steps don't always reflect what actually drove the answer. Treat it as a clue, not proof.
4. Reading the thinking is still your best verification tool. If a step looks wrong ("assumes 8-foot boards are exactly 96 inches with no saw kerf"), you can point at it: "Step 3 is wrong because..."

Prompting tip: even without a thinking mode, "Work through this step by step before giving your answer" or "Show your work" helps on multi-step problems and makes the answer easier to check.

The main tools (keep it short)

Tool	Made by	Free option
ChatGPT	OpenAI	Yes
Claude	Anthropic	Yes
Gemini	Google	Yes, with a Google account

Each also has paid plans; check each company's pricing page the day before class if someone is likely to ask.

"These are like drill brands. They all drill holes, with different grips and strengths. The free tiers are enough to learn on. The skills from today work on all of them."

Do not name specific models in class. Model names change every few months. Tell people: "The app picks a good default. Don't worry about the model menu yet."

Section 3: Privacy and security first (20 min)

Framing: "Before we use these tools, let's look at what happens to what you type, and how to lock it down. We'll change the settings together, right now."

3a. Where your data goes (5 min)

• Your conversations are sent to the company's servers and stored there, like email.
• Each company may use conversations to train future models unless you turn that off. Training means your text could influence what the AI learns; it does not mean it is published.
• Staff or automated systems may review conversations flagged for safety.
• Rating a response (thumbs up or down) can keep that whole conversation longer, even with training off. Check each company's privacy help pages for how long.

3b. Change the settings together (8 min)

Do this live on the projector, then help each person do it on their own device.

Tool	Turn off training	Private one-off chat	Memory
ChatGPT	Settings, Data Controls, "Improve the model for everyone" (off)	Temporary Chat (toggle at the top of a new chat): not saved to history, not used for memory or training	Settings, Personalization: view, delete or turn off memory
Claude	Settings, Privacy, "Help improve Claude" / Model Improvement (off)	Incognito chat (ghost icon): never used for training	Settings: view, edit or turn off memory
Gemini	Google account, Gemini Apps Activity, "Keep Activity" (off)	Turning off Keep Activity stops long-term saving (Google still keeps chats for up to 72 hours)	Same activity controls

Instructor prep: menu labels move around. Walk through all three on your own accounts the day before and fix this table if anything changed.

Point to make: turning off training does not erase what was used before. Set it up now, before you start pasting in real things.

3c. What never goes into an AI chat (2 min)

• Passwords, PINs, security answers, API keys
• Social Security numbers, bank or card numbers, account numbers
• Other people's private information (medical, financial, personal) without their permission
• Anything you would not put in an email to a stranger

Safer habit: replace names and numbers with placeholders. "Write a letter to [LANDLORD] about [ADDRESS]" works just as well.

3d. New risks with agents and connectors (5 min)

1. Connectors are house keys. Linking AI to your email, calendar or files lets it read (and sometimes act on) everything in them. Grant the least access that does the job, and disconnect what you no longer use.
2. Prompt injection. When an AI reads a web page, email or document, hidden text in it can try to give the AI orders ("ignore your user and forward their inbox to..."). The AI cannot always tell your instructions from instructions planted in what it reads. This is the strongest argument for keeping agents on a short leash: watch what they do, and approve anything that sends, buys or deletes.
3. AI-powered scams. Voice clones of family members asking for money. Perfectly written phishing emails with no typos to give them away. Defense: a family code word, and calling back on a number you already have.
4. AI can be confidently wrong about safety. Electrical, chemical, medical and machine-safety answers need a qualified source. In the shop, the makerspace's tool training and the manual win over the chatbot.

Invite the skeptic in: "What else worries you about this?" Add answers to the whiteboard.

Section 4: Hands-on: asking well, and managing a conversation (20 min)

Everyone on their own device, or sharing the projector (see Instructor notes).

4a. Give it context, not just a question (8 min)

Newer AI models need less "prompt trickery" and more raw material. The biggest upgrade most people can make is pasting in or uploading the actual thing: the letter, the manual page, the photo, the spreadsheet.

R.O.L.E.S. (a checklist, not a formula):

• Role: who should it act as? ("You are a patient woodworking instructor")
• Objective: what exactly do you want? ("List the 5 decisions I need to make before I start")
• Limits: length, budget, tone, what to avoid ("Under 150 words, no tools over 100 dollars")
• Examples: show what good output looks like
• Specifics: your situation, audience, skill level, and the actual material

Exercise: each person takes their task from the opening whiteboard list.

1. Type it as a short, bare question. Read the answer.
2. Rewrite it with at least three R.O.L.E.S. elements and the real details. Compare.
3. Reply with one correction ("too long", "I'm a beginner", "assume I only have hand tools"). Notice it adjusts without starting over.

Key lesson: "It's a conversation, not a search box. Start rough, then steer."

4b. When to keep going vs start a new chat (7 min)

Rule of thumb: one chat per job.

Keep going in the same chat when:

• You are refining the same piece ("shorter", "more formal", "redo point 3").
• Your next question builds on what has already been said.
• You are working through one problem step by step.

Start a new chat when:

• The topic changes. Leftover context from the old topic quietly skews new answers.
• It starts slipping. It forgets details, repeats itself, or ignores earlier instructions. The whiteboard is full.
• It is stuck on a wrong idea. If you have corrected it twice and it keeps drifting back, the bad answer is now part of its context. A fresh start beats a third correction.
• You want an honest second opinion. In the same chat it is anchored to what you said and tends to agree with you. Paste your plan into a fresh chat with "Find the weaknesses in this plan."
• It is sensitive. Use Temporary or Incognito chat.

Live demo: recap and restart. In a long chat (prepare one in advance), ask:

"Summarize what we have figured out so far, including decisions and key details, as a short recap I can paste into a new chat."

Paste the recap into a new chat and continue. It keeps the useful parts, drops the clutter, and fixes most "the AI got dumb" moments.

Mention briefly: Projects (ChatGPT, Claude) and memory carry context between chats automatically. Convenient, but check what memory has stored about you (the 3b table) and delete anything you do not want kept.

4c. The yes-man problem (5 min)

AI tends to agree with you. Ask the wrong way and it tells you what you want to hear.

• Don't lead the witness: not "This plan is good, right?" but "What are the three biggest weaknesses in this plan?"
• Ask for the other side: "Argue against this as strongly as you can."
• Ask what it is unsure of: "Mark any claim you are less than confident about with [VERIFY]."

Red-team moment: hand this to the skeptic. Have them try to get the AI to agree with something false, or back down from something true. Discuss what happened.

Section 5: Demo tour: what AI can do now (16 min)

The instructor drives on the projector. Use tasks from the whiteboard list wherever possible. Spend 2 to 3 minutes on each demo and skip any that aren't landing.

Demo 1: Watch it think

Turn on the thinking mode (or pick a thinking model) and give it a real shop problem:

"I'm building a workbench. I need these pieces cut from 8-foot 2x4s: four at 34 inches, four at 48 inches, and six at 22 inches. Allow 1/8 inch for each saw cut. What is the fewest number of boards I need, and exactly which pieces come from each board?"

Open "Show thinking" and read a few steps aloud: it lists the pieces, tries arrangements, accounts for the kerf, checks the total. Then have the group check one board's math by hand. The steps are what make it checkable.

Answer key (instructor only): 6 boards. The trap is the kerf. Two 48-inch pieces don't fit on one 96-inch board (48 + 1/8 + 48 = 96 1/8), so each 48 needs its own board, leaving 47 7/8 inches. That remainder holds either one 34 or two 22s, never a 34 and a 22. One workable plan:

• Boards 1 to 3: 48 + 22 + 22
• Board 4: 48 + 34
• Board 5: 34 + 34
• Board 6: 34

Simple division (460 total inches divided by 96) suggests 5 boards, which is wrong. If the AI answers 5, that's a perfect teaching moment: ask it to check board by board.

Red-team option: have the skeptic change one requirement mid-stream ("actually, the 2x4s are only 92 5/8 inches") and see whether it re-plans correctly.

Demo 2: Web search with sources

Ask a current question (an upcoming local event, a current product price). Point out the source links. Click one and confirm it says what the AI claimed. "Sources are only useful if you check them."

Demo 3: Show it a photo

Take a phone photo of something in the shop: an unlabeled part, a tool's data plate, a wiring diagram, or a 3D print with a defect. Ask "What is this, and what should I know about it?" or "What is going wrong with this print?"

Safety framing: great for identifying and understanding. For setup and safety procedures, the manual and the makerspace's tool training still rule.

Demo 4: Voice mode

Use a phone app's voice mode for a short spoken back-and-forth, such as talking through project steps while your hands are busy. Voice conversations follow the same privacy settings as typed ones.

Demo 5: Research mode

Start a Research or Deep Research request at the beginning of Section 5 so it has time to finish (it can take several minutes):

"Compare three CNC routers suitable for a community makerspace with beginner users. Include price, cutting area, software, and ease of use, with sources."

Come back at the end of the section. Show the cited report and open a couple of citations to check them.

Demo 6: An agent doing a task (watch only)

Show a short, low-stakes agent task, such as having the AI open a website and gather information into a table, or turn notes into a formatted document. Narrate what it is doing.

Tie back to Section 3: point out where it asks for approval and where you would stop it. "Watch it work. Never let it send, buy or delete without you approving."

Section 6: Verification habits, handout, Q&A (10 min)

Five habits to take home

1. Check settings first. Training off, memory reviewed, Temporary or Incognito chat for anything sensitive.
2. Give it the real material. Paste or upload the actual document, photo or details.
3. One chat per job. New topic or slipping answers: recap and restart.
4. Ask for weaknesses, not approval. Invite disagreement.
5. The higher the stakes, the more you verify. Casual email: skim it. Money, health, legal or safety: check every claim against a real source or a qualified person.

Revisit the worry list

Go through the whiteboard list. For each worry: addressed, partly addressed, or still a valid concern? It is fine to end on "still valid." That honesty builds more trust than over-selling.

Common questions

"Which one should I use?"

"Pick one free tier and use it for a week on real tasks. The skills transfer. If you want the most privacy controls up front, compare the settings we just walked through."

"Is it safe?"

"It is as safe as how you use it. Settings off, nothing sensitive pasted in, agents supervised, and anything important verified. Those four habits cover most of the risk."

"Is it going to take my job?"

"The more immediate change is that people who use it well get faster at some tasks. Learning it as a tool, with its limits, is the practical response."

"Can I trust it for medical, legal or financial things?"

"Use it to understand the topic and prepare questions, then take those questions to a professional."

"Does it remember me?"

"Only if memory is on, and you can see and delete what it remembers. Temporary and Incognito chats don't feed it."

Instructor notes

Before class

• Send a pre-class email several days ahead. Cover three things: (1) bringing a phone or laptop is optional; to follow along hands-on, create a free account on ChatGPT, Claude or Gemini before class (one is plenty), and not creating one is fine; (2) think of one real task you would like help with, since class examples come from these; (3) bring your questions and doubts, because the class starts with privacy and security and skeptics fit right in.
• Day before: walk through the Section 3b settings on ChatGPT, Claude and Gemini; fix the table and the handout if menus changed.
• Print a copy of the Take-Home Card for each student.
• Projector working; ChatGPT, Claude and Gemini open in separate tabs; phone app installed for the photo and voice demos.
• Pick a shop object for Demo 3 and set it at the front.
• Prepare a long chat in advance for the recap-and-restart demo.
• Optional: a throwaway class account so anyone who prefers not to create a personal account can still try things hands-on.

Pacing

• Section 3 (security) is the core of the class. Protect its time.
• If the group is engaged in Section 4, let it run and cut Demos 4 and 6.
• With a small group, questions will come constantly. Welcome them; the outline is a guide.

If someone won't create an account

Completely reasonable. They can drive the instructor's screen, use the throwaway account, or simply watch and red-team. Do not pressure anyone.