AI 101 for Marines
Brief AI for a task you need done. Check its answer before you use it.
6 chapters, about 30 to 40 minutes. Free to read; no account required.
If you use AI every day, start at chapter 3.
- 6 chapters
- About 30 to 40 minutes
- No account needed
- 1What you are talking to3 min
- 2Brief it like a Marine6 min
- 3Catch the confident wrong answer6 min
- 4Get one real thing done today6 min
- 5When a chat is not enough3 min
- 6Self-check4 min
Your answers save in this browser. A chapter counts as practiced after its exercises; the self-check needs 6 of 8 right. You can revisit any chapter. Optional feedback sends only what you enter when you tap Send feedback. The optional email signup sends your address separately.
This browser is not saving your progress. New answers may be lost when you leave or reload.
What you are talking to
A chatbot generates text from learned patterns and the context it can see. It can sound confident when it is wrong.
Give it the facts a Marine who checked in yesterday would need. Memory and search may add context. Check which facts the answer uses. Anthropic, the company that makes Claude, gives its own users the same advice: treat the model like a brilliant new employee who lacks your context.
Use Claude, ChatGPT, or Gemini for the exercises. Check their free-plan limits below.
Free plansClaude pricingChatGPT pricingGemini plans
Words you will see
- Chatbot: an app you type or speak to, such as Claude, ChatGPT, or Gemini, that writes back.
- Model: the program inside the chatbot that writes the replies.
- Brief: what you type to it. Most people call it a prompt.
- Context: everything the model can see right now: your brief, what you pasted, and anything memory or search added.
- Memory: a setting that carries facts from past chats into new ones.
- Web search: a setting that lets it read current pages and cite them.
- Hallucination: a confident answer that is not true.
- Tool: a program that carries out a specific job.
Let it draft and explain. Before you act on a number, a date, or a rule it gives you, check it.
Brief it like a Marine
Write 4 parts: task, purpose, constraints, and end state.
Task: Build a run plan. Purpose: Improve my PFT. Constraints: Four mornings, 45 minutes. End state: A weekly table.
When the reply is close
Send one specific fix: "Make week 3 easier." "Half as long." "Use only the numbers I gave you." The chat usually keeps recent messages in view. In a long chat, restate the facts that matter.
Give it your task and facts. Check the reply before you use it.
Catch the confident wrong answer
Use 4 checks to catch a wrong answer: the math, your facts, its source, or a fresh chat.
Why it happens
OpenAI's researchers explain it with a multiple-choice test. A blank answer always scores zero, and a guess sometimes scores, so a model that guesses looks better on the test. Training and scoring can reward guessing. Check specific claims even when the answer sounds certain.
Four checks
- 1Do the math. Dates, money, paces, counts. Ask it to show its inputs and calculation. Verify the result with a calculator or calendar.
- 2Compare it to what you gave it. Check added claims against your facts or a source, especially numbers it could not derive.
- 3Ask where it came from, then open it. For a rule, a fact, or a quote, ask for the source and read the line yourself. A source it names can be wrong too.
- 4Ask again in a new chat. Different answers are a warning. Matching answers can repeat the same mistake. Check the source either way; a new chat may still use saved memory.
Head it off in the brief
Two lines in your brief cut down on this before it starts: "If you are not sure about a fact, say so." and "Quote the line you used." Anthropic's guide lists both. It also says they reduce made-up answers without eliminating them, so the checks still apply.
Trust an answer after it passes the check that fits it: the math, your own facts, or the source.
Get one real thing done today
Pick a task for this week. Build a brief from your answers, paste it into your chatbot, and check the reply.
Fill in what you know. Leave a box empty and the brief shows [fill this in], so you can see what the AI would have to guess.
Keep other people's private details out of public AI chats.
After you run it
Record what you did in your chatbot. This page cannot check it. Mark all 3 after you finish to count this chapter as practiced.
Pick a task and build your brief before you leave.
When a chat is not enough
A tool can save your facts, count dates by a fixed rule, and keep the source beside each task. Check its inputs and rules.
Compare the examples
| Feature | Chat | Saved plan |
|---|---|---|
| Your facts | Give it the lease terms and current date. Check what memory adds. | Keeps the inputs where you can review them. |
| Dates | Can calculate them. Check the arithmetic. | Uses the displayed rule when you change a date. |
| Checks | Read the source and check the result. | Read the source and check the result here too. |
How Muster Out uses this pattern
Muster Out builds a saved separation or retirement plan from your facts. Open a task to check its source and date rule. It can still be wrong.
Muster Out works on Claude Free; Pro at $20 a month gives more room for long chats. Free also works for the text exercises in this course within usage limits.
Use a saved tool for a repeat job. Keep checking its facts, dates, and sources.
Self-check
Get 6 of 8 right, then review any misses. This is a self-check; your answers stay in this browser.
Put it to work
Run your brief today, then pick what comes next.
Help improve AI 101
Optional. Skip this and keep going. Only what you send here is shared.
16 OCT workshop reference
Warfare Command hosted AI Tools for Marine Leaders on 16 OCT 2026. This preparation reference is retained from the completed session.
- The GenAI.mil practical used an MCEN laptop.
- The optional Muster Out setup used a personal device and a Claude account on a personal email. Claude Free works.
- If the phone app cannot open or save your board, try claude.ai in the browser on that device. For help, email feedback@warfarecommand.com.
The 4-part brief and answer checks remain available in this course and carry over to GenAI.mil.
In development
- AI 102: Save your goals and answer preferences.
- AI 103: Find and check answers in your files.
- AI 104: Schedule a weekly check, if your AI supports it.
Get Warfare Command updates
Get new lessons and Warfare Command Monthly. Confirm your address to start. Change your choices or unsubscribe from any email.
This signup starts New lessons and Warfare Command Monthly after confirmation. Privacy
Your transition, run like an op.
Muster Out helps you prepare for life after the Corps. Build your transition plan in your Claude account. Works on Claude Free.