Appendix A — Setting Up Your AI Toolkit

“Prepare your work outside; get everything ready for yourself in the field, and after that build your house.” — Proverbs 24:27 (ESV)

Before the first lab, you need a working toolkit. Here is the good news, and I want you to feel it before you read another line: Concordia has already bought your toolkit for you. The university licenses an AI platform called BoodleBox, and it puts the major premium AI models — the ones people pay $20 a month each for — behind a single Concordia login. If you have a web browser and your Concordia account, you already have everything this whole course requires. A phone works too. You do not need to buy anything, install anything, or ask IT for anything.

I know some of you arrived nervous. You’ve heard AI is expensive, or that it needs a powerful computer, or that you have to be technical to touch it. None of that is true for this class. We are going to walk the path Concordia already paid for, and I’ll be honest with you at every step about what — if anything — costs money. (Spoiler: for you, on campus, it’s nothing.)

One rule governs everything you’re about to set up. Write it where you’ll see it:

You choose the tool. You own the verdict. AI drafts, generates, and accelerates; you decide, verify, and are accountable. AI is an assistant, not an authority.

The tools below are assistants. This appendix gets them working. The judgment stays with you.

Coach’s Note — Everything in Sections A.1 through A.4 is free to you, needs no install, and needs no admin rights — it runs on a school Chromebook, a borrowed laptop, or your phone. Only the optional private-computer path in A.5 installs software, and even that has a fallback. Nobody in this room is priced out. Start at the top and stop when you have what your next lab needs.

A.1 — What You Actually Need

The backbone of this entire course is BoodleBox — Concordia’s AI platform — in a browser. That’s it. Inside BoodleBox you’ll reach every major AI model, a library of specialized bots, and the tools to compare them, all from one Concordia login. Most weeks use one chat. A few weeks add a specialized bot or upload a file, and exactly one week offers an optional download for people who want to run AI privately on their own machine.

Here is the whole landscape, honestly:

On campus you will never be required to pay for a subscription in this course — Concordia’s license covers you. Free tiers (yours on campus, or Boodle Basic off campus) can be rate-limited — they slow you down or cap you after a heavy burst — but they are more than enough to learn on. When you hit a limit, wait a bit or switch which model is answering (you’ll see how in A.2). I’ll show you what each lab needs in A.4.

Coach’s Note — Why a school platform and not just a random chatbot? This is the whole reason Concordia bought BoodleBox, and it matters most for the privacy chapters. As of 2026 BoodleBox is FERPA-compliant, SOC 2 certified, and does not train its models on your data. That makes it the appropriate place for Concordia coursework and work information — unlike a free consumer chatbot, whose free tier may use whatever you type to improve the model. Even so, the discipline still holds: never paste a client’s private data, a patient record, a student’s identifiable information, or a password into any tool without cause — protect people’s data as a trust, not raw material. A whole appendix is devoted to this; read Appendix C — Responsible & Ethical AI Use before Week 6. For now: practice on public or made-up information.

A.2 — Sign Into BoodleBox (Concordia’s AI Platform)

This is your one setup step, and it takes about two minutes.

Go to box.boodle.ai and sign in. If you’re a Concordia student, faculty, or staff member, choose “Sign in with your EDU account” and use your Concordia login (the same single sign-on you use for campus systems). That’s it — you’re in, with the university’s license behind you.

Off campus, or after you graduate? BoodleBox is built for lifelong portability — as of 2026 your access travels with you. You can sign in with Google or email, and there’s a free Boodle Basic tier that keeps you working when you’re not on Concordia’s license. (There are paid personal tiers too — roughly a Boodle Unlimited plan around $16/month and a Boodle Enterprise tier, which is what an institution like Concordia licenses. As of 2026; prices move. You do not need a paid personal plan for this course.)

Coach’s Note — You are not signing up for three separate services and juggling three passwords this term. That’s the old way, and it’s why so many people gave up. One login at box.boodle.ai puts every model this book names — and hundreds of specialized bots — in one place.

A two-minute tour of the room

Labels and model names move fast, so I’ll describe the thing each control does rather than bet on an exact button. As of 2026, here’s what you’ll find:

• The chat and the bot selector. Every conversation is a chat, and every chat starts with BoodleBot (@boodlebot) — a friendly default that orchestrates the others. Near the message box is a bot selector that opens a picker organized into categories like Popular, AI Models, Boodle Bots, Custom Bots, and Discover, with search and favorites. That picker is how you choose who answers.
• Type @ to add or compare models (multi-bot chats). This is the flagship, and it changes how this whole book works. Type @ in the message box to open the picker and drop another model right into the same conversation — so you can put several models side by side in one chat and compare their answers. Where the old edition of this course told you to “open three browser tabs,” you’ll now just @-mention three models in one chat.
• Prompt Modes / Coach Mode. A control for prompt modes, including a Coach Mode that gives you contextual, step-by-step guidance while you work — it builds your prompting skill as you go. You’ll lean on this in the prompting weeks.
• Attach Knowledge. An “Attach Knowledge” option (and an upload area) that lets the AI answer grounded in your files — a report, a policy, a spreadsheet — instead of just its training. This is the engine of the Week 7 summarize-and-verify lab.
• Folders. Chats organize into Folders, so a term’s worth of work doesn’t turn into one endless scroll.
• Boxes (group chats). A Box is a shared chat you can invite both people and bots into — a professor, a classmate, a teammate, plus whichever models you want — all in one place. Instructors can even see student work, which makes AI use visible and assessable. This is the collaboration angle for the Week 6 meeting lab and any group work.
• Build Bot (custom bots). You can build your own bot: give it a name, choose which AI model powers it, write its instructions and persona, and attach reference Knowledge — then use it or share it. That’s what turns your prompt library into a reusable tool in Week 12.

Don’t try to master all of that today. Right now you just need to know the room exists and where the light switches are.

Verify it works — with one prompt

Don’t just log in. Prove it answers, and get your first rep of the muscle Week 2 trains. Start a new chat and paste in this sentence:

Explain what a large language model is to a busy professional, in three sentences, with no jargon.

BoodleBot will answer. Now do the interesting part: type @, add a second model, and then a third — as of 2026 you might pick, say, @chatgpt-5.6, @claude-opus-5, and @gemini-3-pro — and send the same question again so several models answer it in the same chat. You’re checking two things. First, that the tool responds — if you get answers, your toolkit is live. Second, and more interesting: notice they don’t answer identically. One is warmer, one is tighter, one adds an example. Keep that chat. That side-by-side is exactly the muscle Week 2 trains, and you just did your first rep — in one window, not three tabs.

Coach’s Note — In a multi-bot chat each reply is labeled with the bot that wrote it, so you always know which model said what. If you ever want to confirm what you’re talking to, ask it: “In one sentence — what are you, and who made you?” The picker holds far more than the big three — a web-search model like @perplexity, image bots, hundreds of specialized helpers. Appendix B — The AI Tool Directory maps them to what each is best at. For now, don’t over-collect. A few bots you use beats a hundred you favorited once.

Fallback (keep this in your back pocket). If you ever can’t reach BoodleBox — off campus with no login, or the site is down — every task in this book also works on the free tiers of the public assistants: ChatGPT (chatgpt.com), Claude (claude.ai), Gemini (gemini.google.com), or Perplexity (perplexity.ai). Sign up with an email or Google account, no credit card. The book still functions; you’ll just be switching tabs instead of typing @.

A.3 — Set Up Your Prompt Library (a plain notes doc)

The single habit that separates professionals who get value from AI from those who don’t: they save the prompts that worked. A good prompt is reusable capital. You write it once, refine it, and reach for it for the rest of your career. Week 12’s whole project turns this into a reusable custom bot inside BoodleBox — but you start the container now, empty, on day one.

You don’t need special software. Pick whichever of these you already have:

• A Google Doc (free, syncs everywhere, easy to share with a teammate later)
• Apple Notes, Microsoft OneNote, or your phone’s built-in notes app
• A plain text file (prompt-library.txt) on your desktop

Create it, title it “My Prompt Library,” and give each entry the same simple shape:

=== Task: <what you're trying to do> ===
Bot/model I used: <@boodlebot / @chatgpt-5.6 / @claude-opus-5 / other>
The prompt:
<paste the exact wording that worked>
What worked / what I'd change:
<one line of notes>

Add your first entry right now: the “explain a large language model” prompt from A.2, and a note about which model’s answer you liked best. That’s the library started. Every week, when a prompt earns its keep, it goes here. By Week 12 you’ll organize it by role and task — and then feed your best ones into a Build Bot custom bot so they’re one click away. The wise, Scripture says, lay up knowledge (Proverbs 10:14, ESV). This little doc is where you lay up yours.

A.4 — Which Lab Needs Which Tool

So you never over-prepare or panic, here is every week mapped to the BoodleBox feature that does the job — your default this term. When a week points you to a specialized bot or tool, Appendix B tells you which one and where to find it.

Read that table and breathe. Fifteen of sixteen weeks run entirely in your browser on the platform Concordia already paid for. Only Week 11 even offers a download, and it’s optional. Nobody needs a $2,000 laptop for this course.

Fallback in one line — any week above also runs on the free public tools if you can’t reach BoodleBox: use a free assistant (ChatGPT / Claude / Gemini / Perplexity) in place of a @-mentioned model, its file upload in place of Attach Knowledge, its image mode in place of an image bot, and a shared doc in place of a Box. Same task, more tabs.

One more free tool worth naming: several labs fill in a small table or matrix (Weeks 3, 7, 12, 16). Any free spreadsheet works — Google Sheets (free with a Google account), Excel or Numbers if you own them, or even a table in a plain document.

A.5 — Optional: Run AI Privately on Your Own Computer

This one section is different from everything above, and I want to be clear about that up front. A.5 is optional, it installs software, and it is the only part of this course that asks anything of your hardware. It exists for one lab — Week 11’s Frontier vs Local Showdown — where you compare a big cloud model against a smaller one running entirely on your own machine, with your data never leaving the room.

Before you reach for it, understand where BoodleBox already sits on the privacy map. There are really three postures:

1. A random public chatbot — convenient, but its free tier may train on what you type. Not for Concordia data.
2. BoodleBox — the vetted institutional middle: FERPA-compliant, SOC 2 certified, and no-train (as of 2026). This is the right home for Concordia coursework and work content. For almost everything, this is the privacy answer.
3. A model on your own machine — the maximum: nothing leaves your computer at all. That’s what A.5 lets you feel firsthand.

That privacy tradeoff is the point of Week 11: some information is too sensitive to send to anyone’s cloud, and guarding the deposit entrusted to you (1 Timothy 6:20, ESV) is a professional duty, not a preference. Running a model locally lets you experience the far end of that spectrum with your own hands.

Before you try it, two honest cautions:

1. It needs your own computer, with permission to install apps. A locked-down work or school laptop usually won’t allow it — that’s fine, use the fallback below.
2. It needs a reasonably modern machine. A rough rule as of mid-2026: a small (7–8 billion parameter) model at the common 4-bit size needs about 4–5 GB of free memory to run, so 8 GB of RAM is a bare floor and 16 GB is comfortable. Apple Silicon Macs (M-series) do this especially well. Older or low-memory machines will be slow or won’t run it — and that’s okay.

The gentlest way in: LM Studio

For non-technical users I recommend LM Studio — it’s a normal desktop app with a chat window and a built-in model browser, no typing commands required:

1. Go to lmstudio.ai and download the app for your operating system; install it like any other program.
2. Inside the app, search its model catalog and download a small model (look for a 7–8B model in a “Q4” size — the app labels which ones fit your machine).
3. When it finishes, open a chat with that model and ask it anything. If it answers, an AI is now running entirely on your computer, with no internet — you can even unplug your Wi-Fi and it keeps working.

Prefer a command line, or want the tool most guides assume? Ollama (ollama.com) is the popular alternative — install it, then run ollama run llama3.1:8b in a terminal to pull and chat with a small model. Same idea, more technical feel. Either one satisfies the Week 11 lab.

If your machine can’t do it — the no-install fallback

You can complete Week 11 without installing anything. The project gives a no-install path: you compare a frontier cloud model against a small, lighter cloud model on the same tasks — for instance, in BoodleBox, @-mention a flagship model and then a “mini / nano / flash” tier and run them side by side — and you reason through the privacy tradeoff from the reading and the in-class demo rather than by hosting a model yourself. You lose none of the credit and none of the lesson — the lesson is the privacy-versus-capability tradeoff, and you can learn that with your hands or with your head. Choose the path your hardware allows and don’t fight it.

Coach’s Note — Don’t buy a computer for this course, and don’t feel behind if A.5 isn’t for you. Running a model locally is a genuinely cool thing to have done once — it demystifies the whole business — but it is a bonus rep, not the main lift. The professional skill this course builds is judgment, and judgment doesn’t require a graphics card.

A.6 — When Something Won’t Work

A few snags catch almost everyone. None of them are your fault, and all are quick fixes:

• “My Concordia login won’t get me in.” Make sure you chose “Sign in with your EDU account” at box.boodle.ai and used your Concordia credentials, not a personal password. If SSO still balks — new account, wrong campus profile — sign in with Google or email to keep moving, and check with your instructor or Concordia IT so your EDU access gets sorted.
• “I hit a limit / it told me to slow down.” That’s a rate limit working as designed. Wait a bit, or in the same chat @-mention a different model and continue — one of the quiet perks of having every model in one place.
• “It won’t take my file.” Upload caps size and sometimes file type. For Week 7, use Attach Knowledge with a smaller excerpt, paste the key text directly, or split a long document into parts.
• “The screen looks different from these steps.” These platforms redesign constantly, and model names change. The button labels drift; the task doesn’t. Look for the obvious “new chat,” the @ to add a bot, or the upload/Attach Knowledge control — it’s there under some label.
• “I can’t reach BoodleBox at all.” Use the fallback from A.2 — a free public assistant (ChatGPT / Claude / Gemini / Perplexity) runs every lab. You lose the one-window @-mention convenience, not the learning.
• (A.5) “The local model is painfully slow or won’t load.” Your machine is under-powered for that model — pick a smaller one, or just use the no-install fallback. No penalty.

A.7 — Submitting Your Work

Every project in this book is submitted the same way: one link to a shared folder, or one combined PDF. No GitHub, no code, nothing technical. Here is the whole procedure once, so every project can simply say “submit per Appendix A.”

Option 1 — a shared folder (recommended).

1. Make one folder per project in Google Drive, OneDrive, or Dropbox, named like the project asks (e.g., p1-first-contact).
2. Put every deliverable inside — documents, tables, screenshots — using the file names the project lists.
3. Turn on link sharing: in Google Drive, right-click the folder → Share → change “Restricted” to “Anyone with the link — Viewer.” (OneDrive: Share → “Anyone with the link can view.” Dropbox: Share → Create link.)
4. Test the link before you submit it: open it in a private/incognito browser window. If you can see the files while signed out, so can your instructor. If you get a permission wall, fix step 3 — a link the grader can’t open is the most common submission failure there is.
5. Submit the link wherever your course collects work (Canvas, email, or whatever your instructor names).

Option 2 — one combined PDF. If sharing links is blocked where you work or study, export everything into a single PDF (most word processors will Print → Save as PDF; screenshots can be pasted onto pages) and upload that file instead.

Three rules, every week:

• Names matter. Use the file names from the project’s Submission section — the grader is checking against that list.
• Nothing sensitive. No real client names, patient details, student records, or credentials anywhere in a submission — invented details only (Appendix C is the rule book).
• The link must open. Test it signed out, every time.

A.8 — Verify Your Toolkit, Then Count the Cost

Before Week 1, confirm the pieces work. This takes five minutes:

• BoodleBox is live: you signed into box.boodle.ai (Concordia EDU account, or Google/email off campus) and BoodleBot answered your A.2 verify prompt.
• You’ve met the @ picker: you added a second model to that chat and saw two answers side by side.
• (Optional) Mobile: you’ve opened box.boodle.ai in your phone’s browser and signed in.
• Prompt library started: your “My Prompt Library” doc exists and has its first entry.
• You know where the map is: you can find the A.4 table to check what your next lab needs.
• (Optional, Week 11 only) Private path: LM Studio or Ollama answers a question offline — or you’ve noted that you’ll use the no-install fallback.

If those are true, your toolkit is ready and you owe no one a dollar.

Tear down what costs — count the cost before you commit

Here is the discipline that keeps a free course free. On campus, Concordia’s license covers everything above at no cost to you. But a few things in this space can quietly start charging — mostly off campus or after you graduate:

• Watch the “upgrade” nudges. BoodleBox and every public tool will offer you a paid personal plan (BoodleBox’s own runs roughly $16/month as of 2026; the public assistants push a ~$20/month “Plus / Pro” tier). You do not need one for this course. If you ever choose to try a paid tier, set a calendar reminder and cancel before it renews.
• Free trials of specialized tools (some image, video, or voice tools in Weeks 9–10) may ask for a card for a trial. Prefer the ones with a true no-card free tier; if you start a trial, write down the cancel-by date the day you start it.
• The local models in A.5 cost nothing to run — no per-use charge — but they use your electricity and disk space. Delete models you’re done with from inside LM Studio or with ollama rm.

That habit — sit down first, add up what a thing will cost, and only then commit — is not just budgeting. It’s wisdom the Lord Himself put in the mouth of the Coach:

“For which of you, desiring to build a tower, does not first sit down and count the cost, whether he has enough to complete it?” — Luke 14:28 (ESV)

You are building something this term — an AI-augmented way of working that will outlast the class, and thanks to BoodleBox’s lifelong portability it can travel with you after Concordia. Count the cost of the tools before you lean on them. Lean first on what the university already provides. Keep the money, the data, and the final decision in your own hands. You choose the tool. You own the verdict.

Now go sign into BoodleBox. I’ll see you in Week 1.

Up next: Head into Chapter 1 — The AI Revolution — with your toolkit live. Keep Appendix B — The AI Tool Directory open when a lab names a specialized tool, read Appendix C — Responsible & Ethical AI Use before you paste anything real, and use Appendix D — Glossary whenever a word is new. See you in the gym.