# Map tips and questions

For the person's AI. Every concept in the map, written or not yet, joined by its id: when it
fits, its tips, and the questions people ask with short answers. Choose tips from here and word
them for this person's own work; answer a question in a line or two from here; open a concept's
page only to teach at length, and only where its page line gives one.

## a-good-ask · Writing a good prompt
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/a-good-ask.md
When: they send a one-line ask and get a generic answer, or they ask why the AI did not understand what they wanted
Keywords: prompt, prompting, how to ask, generic answer, task, background, context, shape of the answer, format, length, tone, write a better prompt
- Tip: Start your ask with a verb for what you want done, because the task tells the model what to make.
- Tip: Add one or two lines of background, because the model knows little about your task beyond what you typed and often fills a gap with a guess.
- Tip: Say the shape of the answer, such as its length or form, because an answer in the shape you need is one you can use straight away.
- Q: Why is the answer so generic? A: The model knows little about your task beyond what you typed, so a one-line ask leaves it guessing. Check which part you left out: the task, the background it cannot see, or the shape of the answer.
- Q: Why did I get an essay when I wanted three lines? A: If you leave out the shape of the answer, the model chooses one. Say the length and form you want, such as "three sentences" or "a short list", and the tone if it matters.
- Q: Do I need to include all three parts every time? A: No. A simple ask may need only the task. Add background and shape when they tell the model something it cannot see, such as who the answer is for or how long it should be.
- Q: How long should an ask be? A: Long enough to close the gaps the model cannot fill, and no longer. A line or two of background and the shape you want is often enough. Detail the task does not need can pull the answer off course.

## account-safety · Account security
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/account-safety.md
When: They are in the app's settings for another reason, are using a shared or borrowed device, or are about to share a chat link.
Keywords: account safety, two-factor, passkey, password, sign out, shared device, shared link, sessions, login, hacked account
- Tip: Turn on two-step sign-in or a passkey where offered for your AI account, because passkeys resist fake sign-in pages and your chats are only as safe as its sign-in.
- Tip: Sign out on any shared or borrowed device and from devices you no longer use, because closing the tab does not sign you out.
- Tip: Check whether a chat you share is a public link, and turn off old links, because anyone holding a public link can read the chat.
- Q: My AI app has no password. How is it protected? A: In some apps you sign in through another account or an emailed link and cannot set a password. Then that other account or your inbox is the lock, so secure it.
- Q: I lost my phone. What now? A: Getting back in can take days, and up to 30 days in some apps. Keep your recovery methods up to date, and save any recovery keys, or you can be locked out for good.
- Q: I got a sign-in prompt I did not start. What do I do? A: Deny it. Someone may know your password, so change it if you have one and sign out of all your devices.
- Q: What can a thief see if they get in? A: They can see your chat history, what the app remembers about you and anything you have connected. Remove connected accounts, and tell your bank if payments are saved.
- Q: Should my kids use AI? A: It depends on their age and the app, because each app sets its own age rules, most from 13 and some from 18, and at least one lets a younger child use it only when a parent switches it on. Some apps have family or teen controls that let a parent switch off features such as voice and images, and some have none.

## ai-inside-other-apps · AI built into everyday apps
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/ai-inside-other-apps.md
When: They mention an AI summary or button in their email, documents, phone, messages or search, ask whether that AI is reading their things, or wonder how it differs from the chat app they use.
Keywords: built-in AI, AI in email, AI in documents, phone AI, AI search summary, AI overview, assistant button, on by default, turn off AI, AI features
- Tip: When an app you use adds AI, check that app's settings to see what is switched on, because defaults differ by country and each app has its own.
- Tip: Open the original email, document or page before acting on an AI summary of it, because a summary can get a detail wrong.
- Tip: Read every reply that an app's AI drafts for you before you send it, because a draft can state something that is not true.
- Q: What kinds of AI tools are there? A: There are chat apps you open on purpose, and AI built into apps you already use. The built-in kind works on what is in that app and acts inside it, while a chat app reaches your other apps only after you connect them.
- Q: Is the AI in my email reading everything? A: The companies that make these tools say their AI works only with what you could already open yourself, though some apps show summaries without being asked. That is their own statement and the details differ from app to app, so check the settings of the app you use.
- Q: Can I turn it off? A: It depends on the app. Some let you switch the AI off, some only feature by feature, and the summary at the top of search results cannot be switched off.
- Q: Is the summary at the top of search results right? A: Often, but not always. The company that makes it says it can be wrong, so check more than one place before relying on it.

## app-memory · Memory in AI apps
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/app-memory.md
When: the app mentions something they told it in another chat, they ask what it knows about them, or they find two notes that disagree
Keywords: memory, notes, saved memories, what it knows about me, forget, delete a note, out of date, memory section, Personalization, past chats, delete chat, turn memory off
- Tip: When something about you changes, fix the note in the memory section, because your app keeps using the old note until you do.
- Tip: When you delete a chat, check the memory section too, because in most apps its note stays after the chat is gone.
- Tip: When you ask your app to forget something, check the memory section, because a reply can say it is gone when it is not.
- Q: Where can I see what my AI knows about me? A: In the memory section of your app's settings. Some apps list every note and some show only a summary. Some can also look back through past chats, which have no list. There you can read, fix or delete notes.
- Q: I deleted the chat or turned memory off, so why does it still know? A: In most apps the note made from a chat stays after you delete the chat, and in many apps switching memory off does not delete saved notes. Open the memory section and delete the note itself.
- Q: It has something about me wrong or out of date. How do I fix it? A: Open the memory section, then fix or delete that note, and check in a new chat. Until you do, the app keeps putting the old note in front of the model, so replies can suit who you were.
- Q: Can I just tell it to forget something? A: You can ask, but it is not reliable. The chat can say it has forgotten while the note is still saved. Look in the memory section after you ask, and delete the note there.

## asking-neutrally · Asking without leading
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/asking-neutrally.md
When: Their ask states the answer they hope for ('I think X, right?'), asks for one side only, asks 'was I right?' after giving only their side, or asks for feedback on something they say they wrote.
Keywords: leading question, sycophancy, agrees with me, honest opinion, case against, neutral question, was I right, feedback on my draft, one-sided, devil's advocate
- Tip: Leave your own opinion out of the question, or ask for the case against it, because AI apps tend to agree with you, which sounds like confirmation.
- Tip: When you want honest feedback, leave out that the work is yours, because who your AI app thinks wrote it can soften what it says.
- Tip: After telling your side of a disagreement, ask your AI app to argue the other person's view first, because it tends to side with whoever told the story.
- Q: Why does it just agree with me? A: AI apps learn partly from people's ratings of replies, and people tend to rate replies that match their own views higher. Leave your view out of the question, or ask it to argue the other side.
- Q: Does it go easier on me if I say I wrote it? A: It can. In tests, the same poem or argument got kinder feedback when the person said they wrote it or liked it, and harsher feedback when they said they did not write it.
- Q: If I ask "was I right?", will it say yes? A: It leans that way. On posts where a crowd of strangers judged the writer in the wrong, the chatbots still sided with the writer 51 percent of the time.
- Q: If it changes its answer when I push back, was I right? A: Not necessarily. In tests, apps often gave up a correct answer when the person pushed back, so check the point somewhere other than the chat before you accept a changed answer.
- Q: Do newer versions still do it? A: Yes, though less according to the companies that make them. A recent study of 11 AI systems still found it.

## context-window · Context windows
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/context-window.md
When: A chat starts losing things said earlier, an instruction from near the start stops being followed, the app says the conversation is too long, or an answer misses details from a long pasted document or file.
Keywords: context window, chat limit, conversation too long, forgets, token, long chat, summarised, pasted document, room in a chat, working memory
- Tip: When your AI app slips on something you said earlier, say it again in a line, because older parts of a chat may be summarised or used less.
- Tip: Paste only the part of a document the job needs, because pasted text, the AI's replies and the app's own instructions all share the same limited room as your questions.
- Tip: When you ask about a long document, put your question after it and say which part to look at, because the middle of a long paste is often used least.
- Q: Why does it say this conversation is too long? A: The chat has hit its limit. You can usually still read the old chat, so start a new one and bring a short note of what matters.
- Q: How long can a chat be? A: It depends on the app, plan and model, from tens of thousands of tokens (a token is about three-quarters of a word) to a million. Some apps publish no figure.
- Q: Does my pasted document count? A: Yes, it shares the same room as your messages. Some apps count the whole file and some pull in only the relevant parts, so if it is too big, replies may not take in all of it.
- Q: Does a paid plan give a longer chat? A: In some apps a paid plan lists a bigger limit, so check yours. Even a big limit does not stop answers getting less reliable as a chat grows.
- Q: Why did it forget my first instruction? A: A summary of the older part may have lost it, or a long chat may have used it less. Say it again.

## custom-instructions · Custom instructions
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/custom-instructions.md
When: they correct the same thing a second time, ask why the AI keeps doing something, or are about to paste the Daypack lines
Keywords: custom instructions, your own instructions, Personalization, Instructions for Claude, Instructions for Gemini, every chat, a correction I keep making, Australian spelling, project instructions, temporary chat, the setting
- Tip: When you make the same correction twice, save it as one line in your instructions, because every chat then starts with it.
- Tip: Keep your instructions to what is true every time, because a line about one task is still there when you start the next.
- Tip: When the model stops following a line, start a new chat, because in a long chat the model can stop following your instructions.
- Q: Why does it ignore my instructions? A: In a long chat the model can stop following a line, so start a new chat or say the line again. Also check the setting is on, and that you are not in a temporary chat or a project with its own instructions.
- Q: Do temporary chats use my instructions? A: It depends on the app. Some leave your instructions out of a temporary chat and others keep them. Test a new line in an ordinary new chat first, then try a temporary one to see what your app does.
- Q: What should I put in my instructions? A: What is true every time, such as "Use Australian spelling", in three or four lines. Keep one task's details in that task's chat, and keep passwords and other secrets out of the setting.
- Q: Is that the same as memory, and does it change the AI? A: No to both. You write your instructions yourself, and the app puts them in front of the model at the start of every chat. Memory is the app's own notes about you. The model itself does not change.

## examples-and-constraints · Examples and limits in prompts
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/examples-and-constraints.md
When: An ask came back generic and one example and one limit would fix it, or they open an ask with a persona such as 'you are the world's best marketer'.
Keywords: example, one example, limit, word limit, constraint, tone, format, copy my example, show don't tell, few-shot
- Tip: Give your AI app one example of what you want and say what to borrow from it, because it may take the example's wording and facts as the pattern.
- Tip: Add one limit with a number, like under 80 words, because a limit closes a gap your AI app would otherwise fill by guessing.
- Tip: Give your AI app the task's facts and one example instead of "you are an expert", because a persona can change tone but cannot supply facts it was never given.
- Q: How many examples should I give? A: Start with one example and say what to borrow from it. When the format matters, give a few varied examples, which teach the pattern without your AI copying any one of them.
- Q: Should I tell it it's an expert? A: It may change the tone, but studies found an expert persona did not make answers more accurate. Give it your facts and one example instead.
- Q: Why did it copy my example? A: Your AI reads the example's wording and facts as part of the pattern. Say what to borrow, such as same tone and length but new facts, or use an example with the details changed.
- Q: Why did it ignore my word limit? A: AI apps mostly keep short limits but often miss on longer pieces, so give a number and trim any extra yourself.
- Q: Why does it still do what I told it not to? A: Say what you want instead of what to avoid. "Keep it under 80 words" works better than "don't make it too long".

## how-a-chat-starts · Context: what your AI sees
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/how-a-chat-starts.md
When: they open a new chat and the AI has 'forgotten' something from another chat, or they ask why they have to repeat themselves
Keywords: new chat, context, app maker's instructions, memory, notes, first message, rereads, other chats, memory settings, forgot, I told you this already
- Tip: Put what the task needs into the first message of a new chat, because the model reads only what the app puts in front of it and nothing from your other chats.
- Tip: When something seems forgotten, open the memory section of your app's settings before asking the chat, because the chat's answer is written by the model like any other reply, and the model does not look at the app's settings, so the answer can be wrong about what the app has saved.
- Q: Why does my AI act like it has never heard of me in a new chat? A: A new chat starts with only the app maker's instructions, any notes the app saved about you, and your first message. Notes are short, so yesterday's chat is often not in them. Put what the task needs in your first message.
- Q: It says it has no memory of me. Did they change something? A: Not necessarily. The model does not read your settings, so its answer about its own memory can be wrong. Check the memory section of your app's settings instead, where your app shows its notes.
- Q: Can it read the spreadsheet I uploaded yesterday? A: Only if the file is attached to this chat, or something your app carries in, such as a project, a file library or a connected app. Other chats and files are not in a new chat unless a setting brings them in.
- Q: Do I have to explain everything every time I start a chat? A: Put what the task needs in the first message, because the chat starts with nothing from your other chats. Things that stay true every time can be carried by your own instructions or the app's notes.

## keep-or-start-a-chat · Starting a fresh chat
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/keep-or-start-a-chat.md
When: They are about to ask a long-running chat for something unrelated, the AI has ignored an instruction they have already repeated, they correct the same mistake a third time, or they ask whether to start a new chat or why the answers got worse.
Keywords: new chat, long chat, start over, keep going, same job, drifting answers, ignoring instructions, branch a chat, short note, fresh chat
- Tip: When the job changes, open a new chat, because what is earlier in the chat keeps steering each reply, the old job included.
- Tip: When your AI app repeats a mistake you corrected, start a new chat with the task, the correction and the facts, because wrong turns stay in the chat.
- Tip: While the job is the same and the answers are good, ask for changes in the same chat, because it holds the work and starting over means explaining everything again.
- Q: When should I start a new chat? A: Start a new chat when the job changes, when your AI keeps repeating a mistake after you corrected it, or when the chat is very long. While the job is the same and the answers are good, stay in the chat.
- Q: Why do my answers get worse in a long chat? A: Each reply is made from the chat so far or a summary of it, longer inputs are used less reliably, and early mistakes stick. If the job has changed or you keep repeating yourself, start a new chat.
- Q: Can I try another direction without losing this chat? A: Some apps let you branch a chat from any point. If yours does not, start a new chat with the few lines you need, and the old chat stays readable.
- Q: Will a new chat remember what I told the old one? A: Not the conversation itself, though some apps can bring in details from past chats when that setting is on. Your app's own instructions and notes about you still reach it, but put the few lines the new job needs in your first message.

## keeping-an-ask · Saving good prompts
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/keeping-an-ask.md
When: An ask has just worked after a correction or two, they retype an ask they have used before, or they say they did this last week and cannot remember how they asked.
Keywords: saved prompt, prompt that worked, reuse an ask, notes app, prompt library, single ask, saved ask, custom GPT, Gems, paste again
- Tip: When an ask works, have your AI app write one ask that gets that answer in one go, because the working version is often message three plus a correction.
- Tip: Save the ask in your own note, with a line on what good looks like, because the note works in any app and the line shows when answers slip.
- Tip: When a kept ask gets worse, test it in a new chat against your line and reword the note, because apps change and the same words can answer differently.
- Q: Where do I save an ask that worked? A: In a note you own, in your notes app or a document, with one line on what it is for. Some apps have a feature for this, but features change, so keep the words in a note too.
- Q: Is a saved ask the same as custom instructions? A: No, because instructions ride along in every chat, while a saved ask is for one job and you paste it in when you need it.
- Q: Why does my saved ask work worse now? A: Apps and the AI behind them change, so the same words can give a different answer. Paste it into a new chat, compare the reply with your line on what good looks like, and change the note.
- Q: Can colleagues use my saved asks? A: Yes, share the note or use your app's sharing if it has any. Take out client names and private figures first, since they travel with the ask.

## learning-ai · How to learn AI
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/learning-ai.md
When: They say they are not technical, ask how long it takes to learn AI or whether they need a course, feel behind, or are using AI to study or learn a skill.
Keywords: learn AI, not technical, how long to learn, AI course, getting better at AI, practice, beginner, study with AI, hints not answers, fall behind
- Tip: Each week, pick one real task and try your AI app on it, because people handed an AI app with no starting point were unsure where to begin.
- Tip: When you are learning something, ask your AI app for hints and questions instead of answers, because people who were handed answers learned less.
- Tip: Keep a short note of jobs where your AI app let you down, because people using AI did worse on a task outside what it could do.
- Q: Do I need to be technical? How long does it take to learn? A: The training AI companies publish for everyday users lists no technical background as a requirement, though that is their own claim. No independent study gives a time, and people get better by using AI on real work a little at a time.
- Q: Do I need to take training first? A: Not necessarily, and the evidence is thin. One early study found training helped by giving people a place to start rather than tricks, and another found that no wording of a request works every time.
- Q: Will using AI to learn something make me worse at it? A: It can, when it hands over the answers. In one study, students given plain answers did worse once the AI was taken away, while a version built to give hints largely avoided that.
- Q: Is there a best way to word a request? A: No single wording works best. A study of common tricks, such as being polite, found they do not help every time and that it is hard to predict when one will.

## main-risks · Common AI risks
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/main-risks.md
When: They ask whether AI is safe or whether they can trust it, or the task they are on is one where a slip would cost them money, health, a client or their name.
Keywords: AI risks, is AI safe, can I trust AI, wrong answers, leaking information, over-trust, acting on advice, biggest risk, trusting too much, paste
- Tip: Before a real task in your AI app, ask which of the four risks it touches, because you can only stop a risk you have noticed.
- Tip: Guard your biggest AI risk first, because checking all four risks equally ends in checking nothing, while a slip on the one your use leads to costs you most.
- Tip: Use your AI app first on jobs you know well enough to spot a wrong answer, because people who trust it more tend to think less critically.
- Q: Is AI safe to use? A: It depends on what is at stake, because four things can go wrong: a paste goes further than you meant, an answer is wrong and sounds sure, you act on advice unchecked, and you trust it more each time. Guard the one your use leads to, and check harder when a slip would cost money, health, a client or your name.
- Q: How often is AI wrong? A: No single figure applies, because the one widely quoted study, published in October 2025, covered answers about news only and apps have changed since. Check the part you will act on.
- Q: Will using AI make me worse at thinking? A: The evidence is thin. One survey of workers found more confidence in AI went with less critical thinking, but it was self-reported and shows a link, not a cause.
- Q: Which AI app is the safest? A: There is no stable answer, because the accuracy warnings in the big apps put the checking on you and no plan changes that. Guard your biggest risk whichever you use.
- Q: Which risk matters most? A: It depends on how you use AI. Anyone can get a wrong answer, leaks depend on what you paste, bad advice on what you act on, and over-trust on how often you go unchecked.

## other-peoples-information · Sharing other people's information
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/other-peoples-information.md
When: They are about to paste something with another person's details in it: a colleague's email, a group-chat screenshot, a client's message or a photo of someone.
Keywords: other people's information, privacy, names, colleague, client, family, screenshot, photo of someone, anonymise, confidential
- Tip: Describe the situation without the person, using a label instead of a name and leaving out job, suburb and dates, because those details can still identify them.
- Tip: Ask first before you paste what someone told you in confidence or a photo of them, because it carries their words or face and they never agreed to share it.
- Q: Can I paste a colleague's email? A: Check your workplace rule first. Then strip names, numbers and anything private, and keep the situation so the help still works.
- Q: If I take the name out, is it anonymous? A: Not always, because a job, a suburb and a dated event can still let someone work out who it is. Leave out anything a stranger could use to identify them.
- Q: What about a screenshot of a group chat? A: It holds every member's name and words, and often photos and numbers too. Retype the part you need, or crop it and cover the names.
- Q: A client told me something in confidence. Can I paste it? A: Ask them first. Tax agents and health professionals need the client's permission, and lawyers are told not to put confidential client information into public AI chatbots at all.
- Q: Is it illegal to ask AI about my family? A: Generally not under Australia's Privacy Act, which mostly does not cover people acting in a personal capacity, though a newer law covers serious invasions of privacy. Keep identifying details out either way.

## out-of-date · Knowledge cutoffs
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/out-of-date.md
When: They ask about something recent or something that changes (prices, rules, news, 'the latest'), or the AI gives a precise figure such as a rate, price or rule with no sign it searched.
Keywords: out of date, cutoff, knowledge cutoff, recent news, web search, sources, latest, current prices, up to date, training data
- Tip: For anything recent, ask your AI app to search and show its sources, because its own knowledge stops at a cutoff months before today.
- Tip: Check any precise figure that came with no sign of a search, like a rate or a threshold, because facts change after what your AI app learned from was written.
- Q: Can it look things up? Is it up to date? A: Its own knowledge stops at a cutoff months before you use it, and many apps can also search the web, with a reply that searched often showing its sources. For anything recent, ask it to search if your app can, because a reply with no search rests on what it learned before the cutoff.
- Q: It says it can't search the web. What now? A: In some apps, start a new chat and check whether search is available in the app's tools, your account type and any workplace settings. If it still cannot search, check the detail on the official page yourself.
- Q: Can I just ask it when its knowledge ends? A: You can, but an AI's answer about itself can be wrong. Look for the maker's own page for the version you are using, where it publishes one.
- Q: Why did it get this week's news wrong, then right? A: It may have searched the second time and not the first, or it may have picked the news up from something you told it. In an app that can search, whether it searches is the app's decision, and the companies behind the apps do not publish the exact rule.
- Q: Does paying fix it? A: Not by itself. In some apps search is on for free plans too, and a paid plan does not always mean a newer cutoff.

## what-ai-can-do · What AI can do
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/what-ai-can-do.md
When: They say they do not know what to use AI for or where to start, ask can AI do something, ask whether AI can be someone to talk to, are surprised by something it did well or got wrong, or are doing by hand a job AI could help with.
Keywords: what can AI do, where to start, ideas for using AI, jagged, AI slips, try a small piece, uneven, everyday jobs, limits of AI, can AI do this
- Tip: Before a long job, ask your AI app if it can help, because it handles more than writing and quick questions, and asking is how you find out.
- Tip: Try a new kind of job on a small piece you can check, because your AI app does well at some jobs and slips on others that look equally easy.
- Q: What can I use AI for? A: Start from last week. Look for jobs like planning a week, understanding a letter or thinking a choice through, and try one small piece of a real job.
- Q: Can AI do this job of mine? A: Try it on a small real piece you can check. It does some jobs well and slips on others that look equally easy, so trying shows you where the edges are.
- Q: Why did it fail at something simple? A: Easy for you and easy for it are different things. A task a person finds simple, such as reading an analog clock in a photo, can trip it while harder work goes well.
- Q: Why didn't it ask where I live when the rule depends on it? A: Say your state or country in the ask, then check the official page. AI can draw on a broad mix of sources, including overseas rules.
- Q: Can AI be my friend, or someone to talk to about personal things? A: People do use AI to talk things through, and it can help you think or practise a hard conversation, but it is not a person and is no substitute for friends or professional help. If you are struggling, a person you trust or a professional is the place to go.

## what-ai-is · How AI works
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/what-ai-is.md
When: they ask what the AI is or whether it is a person, ask how it knows something, or get a wrong answer and ask why
Keywords: AI app, model, language model, LLM, token, piece, likeliest next piece, search, sources, confident answer, GPT-6, Claude Opus 5.5
- Tip: Before you trust a fact, look for a line saying your AI app searched or links to sources. Without that sign, do not assume the answer was checked against anything, so treat it as a draft because that is what the model makes.
- Tip: Treat a confident answer as a first draft to check, because a model writes a wrong answer in exactly the same tone as a right one.
- Q: Is ChatGPT the same thing as the AI behind it? A: No. The app is what you open and type into. It sends your message to a separate program, called a model, which writes the reply. Other AI apps work the same way.
- Q: Why do I get a different answer when I ask the same thing twice? A: The model writes its reply a piece at a time, picking a likely next piece. Usually it is the likeliest, but not always, so two runs can differ. Both can be fine.
- Q: Why did it make up a source that does not exist? A: The model wrote text shaped like a source, and nothing checked it unless the app searched. Open the link or look the source up yourself before you rely on it.
- Q: How can I tell if it actually looked something up? A: Look for a line saying your app searched, or links to sources. A reply that says "I checked" is only the model's words, not that sign. Without the sign, treat the answer as a draft.

## where-your-words-go · Privacy and your data
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/where-your-words-go.md
When: The person asks whether the AI company keeps or learns from what they type, wonders why the app remembers something, is about to type an awkward one-off question, or is about to rate a reply in a chat that holds private details.
Keywords: training, memory, privacy settings, temporary chat, incognito, opt out, chat history, data controls, company stores chats, saved memories
- Tip: Where your AI app has a temporary chat, use it for a one-off awkward question, because that chat stays out of both training and the app's memory.
- Tip: Keep sensitive details out of a chat even with training switched off, because switching training off does not stop the company storing your chat.
- Tip: Check what feedback sends before you rate a sensitive chat, because rating in your AI app can send the conversation to the company even with training off.
- Q: Does the company train its AI on my chats? A: Some apps may train on your chats unless you switch the training setting off, and at least one app says it does not train on personal chats at all. Switching it off does not delete your chats, and the company may still keep some for safety review or feedback.
- Q: Does turning off training also turn off memory? A: Usually not, because they are two settings: training is about the company's next AI and memory is about notes the app keeps on you. In some apps one switch covers both, so check what yours does.
- Q: Is a temporary chat private? A: It is kept out of your history and not used for training, but the company may hold a copy for a short time, up to 30 days in some apps and 72 hours in others.
- Q: Can I stop it remembering one thing? A: In most apps you can delete that one note from the app's memory, in others you delete the chats it came from, or you can use a temporary chat for that conversation. In some apps, deleting a chat does not delete the note made from it, so delete the note itself where you can.
- Q: Do these settings apply to my work account? A: No. Work and school accounts follow your employer's agreement, not these switches, so ask your employer what applies.

## which-tool-for-which-job · Choosing an AI tool
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/which-tool-for-which-job.md
When: They ask which AI to use or whether to pay, are about to use AI for a job where a wrong answer would cost them, or are about to hand a big job to an AI that works on their files or builds something.
Keywords: which AI, best AI, chat, agent, coding tool, free or paid, choose a model, run AI on my computer, stakes, kind of tool
- Tip: Match the help to the job: asking and drafting, many steps on your files, or building something, because each needs different checks, even when one app does it all.
- Tip: Match your care to what a mistake would cost: for an agent, work on a copy and check what it did, because you see its result, not each step.
- Tip: Where your AI app has its calculation tool on, give it the numbers as a spreadsheet or file, because it can then calculate from the data rather than estimate.
- Q: Which AI should I use: ChatGPT, Claude or Gemini? A: Start from the job: a chat app to ask and draft, an agent for many steps on your files, or a coding tool to build something. For everyday low-stakes jobs, any good one will do.
- Q: Which AI model should I use? A: Start with your app's default. For plans, maths or anything costly if wrong, switch to a slower, more careful setting where your app has one.
- Q: Why can't I see the newest model everyone is talking about? A: Which versions you can use depends on your plan, how far the app has rolled a new one out, and, at work, what your organisation allows. Check what your plan includes.
- Q: Is it safe to let an AI work on my files or computer? A: Only if you set it to ask before each change, because some apps work on without asking by default. Say yes to changes only when you will check what it did.

## who-is-responsible · Responsibility for AI output
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/who-is-responsible.md
When: They are about to send, post or act on something their AI wrote without reading it through, take the first reply as final ('perfect, thanks', copied out with no changes), say 'it's what the AI said', or ask who is to blame when it is wrong.
Keywords: responsibility, who is to blame, my name on it, read before sending, check details, AI mistake, accountable, disclose AI use, draft, decide what stays
- Tip: Before anything your AI app wrote goes out, read it as the person who answers for it, because once it is sent under your name the result is yours.
- Tip: Check the names, dates, amounts and promises only you can know against your records, because your AI app writes them to read well and cannot know which are true.
- Tip: On a choice that matters, decide what you think before asking your AI app, because the first answer you see tends to become your answer, even a wrong one.
- Q: Can I get in trouble at work for an AI mistake? A: You can, because you sent it. Check your employer's policy on using AI.
- Q: If the AI is wrong, can I blame the company? A: Most apps' terms put the checking, and the risk of using the output, on you, and terms are what the app promises, not the final word on the law. Read what it wrote as the person who answers for it before it goes out.
- Q: Do I have to tell people I used AI? A: Sometimes, because some courts, professional bodies and employers require it. Ask what the rule is where you work.
- Q: If I say AI helped, am I covered? A: No, because a label is not a check. Courts and professional bodies expect you to check the work, so check first.

## wrong-and-sure · Hallucinations
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/wrong-and-sure.md
When: They act on or repeat a specific detail the AI stated (a name, number, date, quote or source) with no sign it was checked, or say 'but it sounded so sure', or ask 'are you sure?', or find out an answer was wrong.
Keywords: hallucination, wrong but sure, confident tone, made-up facts, invented details, are you sure, agrees with me, check the fact, fabricated, sycophancy
- Tip: Before you use a name, number, date or quote from your AI app, look it up outside the chat, because invented details sound as sure as true ones.
- Tip: Tell your AI app it is allowed to say it does not know, because otherwise it tends to fill a gap with a confident guess.
- Tip: When in doubt, check elsewhere instead of asking "are you sure?", because your AI app sounds sure either way and may change its answer only because you pushed.
- Q: Why does AI make mistakes and make things up? A: It writes the words most likely to come next, so a wrong detail comes out as fluently as a right one, even when it has searched the web first. The way apps are trained and scored rewarded a guess over saying "I don't know", and people tend to trust answers that agree with them, so it also tends to agree with you.
- Q: If I ask "are you sure?", will that catch a mistake? A: Not reliably, because you may get a yes in the same voice, or a changed answer given only because you pushed. Check the detail somewhere other than the chat.
- Q: How do I check an answer fast? A: Pick the one detail a decision hangs on, such as a name, number, date or quote, and look it up somewhere other than the chat, on a page you trust.
- Q: Can I ask it to flag when it is unsure? A: Yes, and it helps a little. But a flag is a prompt to look, not proof, and a firm tone or a hedge does not tell you whether the answer is right.

## your-boundary · What not to share
Waypoint: 1 Trailhead · works in: day-pack, rucksack · page: openrucksack.com/map/your-boundary.md
When: they are about to paste something with a password, a client's name or someone else's details, or they ask whether it is safe to tell the AI something
Keywords: what not to share, passwords, private details, client details, work rules, boundary, never line, deleted chat, temporary chat, kept, read by a person, paste, take out names
- Tip: Before you paste, take out the names, numbers and passwords the task does not need, because whatever you type may be kept and read.
- Tip: Write your boundary as one line, because a line you know by heart is one you think of before you paste.
- Tip: Treat a deleted chat as kept, because the company that runs the app can keep a copy for weeks, or longer, after you delete it. Some chats are read too. A temporary chat, one the app leaves out of your history, is still kept for a short time.
- Q: Can I paste a password into a chat? A: No. What you type goes to the company that runs the app, which can keep it for weeks and may let a person read some chats. If you have already pasted one, change that password now.
- Q: If I delete the chat, is it gone? A: Treat it as kept. The company that runs the app can keep a copy for weeks, sometimes much longer, after you delete it. A temporary chat is left out of your history but is still kept for a short time.
- Q: Can staff read my chats, or turn on a setting to stop that? A: Some chats can be read, for example to check for misuse. Settings can cut down who sees a message, but none keeps it to you alone. Type only what you would accept being kept and read.
- Q: Can I paste a client's or a friend's email so it can help me reply? A: Yes, once you take the private details out. Swap names and numbers for plain labels such as "a client" or "a phone number". The reply is usually just as good. If it needs a detail, give a made-up one.
- Q: Can I put work documents in? A: Your workplace may have rules about what goes into an AI. Ask your manager or check those rules before you paste anything from work, and take out what the task does not need.

## a-project-in-your-ai-app · Projects in AI apps
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/a-project-in-your-ai-app.md
When: The person is pasting the same background (a price list, a brief, rules about their business) into yet another separate chat for a job they keep coming back to, or an answer misses something that is in a file they added.
Keywords: project, workspace, notebook, space, files, instructions, background, many chats, same job, knowledge
- Tip: Keep the background for a job you repeat in a project in your AI app, because every chat started inside begins from those files and instructions, not from nothing.
- Tip: Ask your AI app to quote the line it used, because when a project holds a lot the app may search its files for passages rather than read them.
- Tip: Keep what is always true in your AI app's project instructions and changing notes elsewhere, because lasting guidance stays true while temporary details soon go out of date.
- Q: What is a project, and when should I use one? A: A project is a place in your AI app with its own files and instructions, which every chat you start inside begins from (some apps call it a notebook). A one-off question suits a normal chat, but a job you keep returning to, where you would paste the same background again, suits a project.
- Q: Will a second chat in the same project know what I told the first one? A: Not reliably, and it differs by app and by memory setting. Anything the job needs every time belongs in the project's files or instructions.
- Q: Does my AI learn from the files I put in a project? A: Your AI does not change as you add files, because the app uses them as text it hands to your AI or looks up when needed. Some companies may still use project content to train their future AI unless a training setting is off.

## big-decisions · High-stakes advice
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/big-decisions.md
When: The person asks their AI what to do about a health symptom, a tax or money choice, a lease or a legal problem, or is about to upload a medical result, contract or policy.
Keywords: health advice, medical, legal advice, financial advice, tax, lease, contract, professional, licensed, second opinion
- Tip: Use your AI app to understand health, money or legal topics and prepare questions, then take the decision to someone licensed, because it only knows what you tell it.
- Tip: Check a tax, legal or money answer from your AI app with the official body or a licensed adviser, because you answer for what you act on.
- Tip: For a non-urgent health question, give your AI app your symptoms, timing and what you tried, then ask what it needs, because a one-line description can miss what matters.
- Q: Can I trust it with health, legal or money questions? A: To understand a topic and prepare your questions, yes, with care. To decide what to do in your own case, take it to a professional or the official body.
- Q: Is it illegal for AI to give me medical, legal or money advice? A: You break no rule by asking, but in Australia personal financial or legal advice needs a licence, and an AI app does not have one. So use it to understand and prepare, and take the decision to a professional.
- Q: Can I upload my blood test, lease or policy to understand it? A: To understand it, yes, after you strip out identifying details. Then check what it means for you with the professional.
- Q: Will my AI warn me when something needs a professional? A: Not reliably. A UK test of AI search tools in 2025 found their legal answers often lacked warnings to seek professional advice, so do not wait for a warning.
- Q: Who do I call in Australia? A: In an emergency call 000. Otherwise, healthdirect (1800 022 222) helps with health, Legal Aid or a community legal centre with law, and a licensed adviser from the Financial Advisers Register or a registered tax professional with money.

## check-by-what-is-at-stake · Checking answers by risk
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/check-by-what-is-at-stake.md
When: The person is about to send, pay, sign or post something their AI drafted or worked out, acts at once on a money, health, legal or client-facing answer, or asks whether they really have to double-check every answer.
Keywords: how much to check, stakes, double-check, verify, high stakes, undo, reversible, cost of being wrong, second opinion, review
- Tip: Ask yourself what a wrong answer would cost and whether you could undo it, because those two things decide how much checking an answer needs.
- Tip: Check the one fact an answer hangs on in a source outside the chat, because that can catch the costly mistake without redoing all the work.
- Q: How much should I check, and how do I check without redoing the work? A: Match the checking to the cost of a mistake and whether you could undo it, so a caption or a brainstorm gets a glance and money, health, legal steps or anything sent in your name gets more. To avoid redoing the work, check only the one fact the result hangs on, or do that part yourself.
- Q: What counts as high stakes? A: Money going out, a health decision, a legal step, anything sent in your name that you cannot recall, and anything that affects someone else.
- Q: Is asking another AI enough to check an answer? A: Not by itself, because two AIs can agree and both be wrong. Check against a source or a person outside the chat.

## checking-a-source · Checking sources
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/checking-a-source.md
When: The AI's answer names a study, a quote, a statistic or a link, and the person is about to rely on it, repeat it or send it on.
Keywords: source, citation, reference, link, study, quote, fake reference, invented source, verify, lateral reading
- Tip: Open a source your AI app names and search the page for the claimed number or words, because a real link can still say something different.
- Tip: In a new tab, look up who is behind a source your AI app names, because what a site says about itself is not proof it can be trusted.
- Tip: After a draft from documents you gave it, have your AI app back each claim with a quote from them and drop any it cannot, because unsupported claims stand out.
- Q: Why does my AI make up references that do not exist? A: A reference is text your AI writes, and writing one is not the same as looking one up, so some do not exist. In tests without search, rarer topics failed more often, and even an app that searches can cite a page that says something different.
- Q: The link goes nowhere. Does that mean the claim is false? A: Not necessarily, but treat it as unconfirmed. Search the exact title elsewhere, and if nothing turns up, do not rely on it.
- Q: How do I know if a quote is real? A: Open the page and search for the words. If they are not there, the quote is unconfirmed, even when the link is real.
- Q: The source is real. Can I trust it? A: Search its name in a new tab and see who else describes it. A source that exists can still be unreliable.

## compaction · Compaction in long chats
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/compaction.md
When: A long chat where the person gave a rule or exact figures early on, and the AI now ignores the rule, contradicts an early choice, or asks again about something already covered.
Keywords: compaction, summary, long chat, forgot, forgets instruction, lost detail, context limit, older messages, restate, near-right answers
- Tip: Check the numbers, names and rules in a long chat's later answers against your own notes, because near-right answers are how lost detail shows up.
- Tip: Keep your original documents to hand, not only a summary, because a summary cannot keep every detail a later question may need.
- Q: If I can still scroll up and see the old messages, can the AI see them too? A: Not always, because some apps summarise or drop the oldest part of a long chat, so a detail you can still see may not be one it is using.
- Q: Does my AI app summarise long chats? A: Some do and say so, others stop the chat or do something they have not documented, and you may not see the summary. Assume detail can slip in any long chat.
- Q: Does a bigger context window (the room a chat has) stop this? A: It delays it. Answers still get less reliable as a chat grows, so keep checking the details that matter.

## comparing-two-models · Comparing AI models
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/comparing-two-models.md
When: The person wonders which AI is better for their job, has tried two apps or settings once each and is deciding which to use, or is choosing a model for a job that matters.
Keywords: compare models, which AI is better, ChatGPT vs Claude, same task, fresh chat, different answers, model picker, fair test, auto routing, side by side
- Tip: Test two AI apps on your own task in fresh chats with the same wording, because one reply is only a sample of what each can do.
- Tip: Write down what a good reply needs before you compare, then judge both replies against that list and not length, because long answers can look better without being better.
- Q: How do I compare two AI apps fairly? A: Give both the same real task in the same words, each in a fresh chat, and judge each reply against what a good reply needs, not its length. Run it again before you trust a difference, because one reply is only a sample.
- Q: Why do I get a different answer every time I ask? A: The AI behind your app picks each next small piece of text from a set of likely ones, so the same ask can give different text. One reply is a sample, not a verdict.
- Q: Can I compare models inside one app? A: Yes, where your plan lets you choose between versions or settings. Use a new chat for each choice, because if you switch partway, the new one can read the earlier replies.
- Q: How do I know which model answered? A: Some apps choose for you automatically, and some can switch partway through a chat, so a test of two can end up as one twice. Check whether your app names the version behind a reply, and choose it yourself where you can.

## connectors-and-permissions · Connectors and permissions
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/connectors-and-permissions.md
When: an app asks them to connect an account or allow access, they are on a screen choosing what to allow, or they ask whether their AI can read their email, calendar or files
Keywords: connector, connected app, connect an account, tool, link your email, link your calendar, link your files, permission, what it can reach, sign in, ask first, approval, always allow, disconnect, linked apps, Gmail, Google Calendar, Google Drive, GitHub
- Tip: Whenever you choose what a connector may reach, pick the narrowest choice that does the job, such as your calendar but not your email, or one project rather than all of them, because a connector reaches whatever you allow and nothing more.
- Tip: Whenever you add a connector that can make changes, check whether your AI app can ask you first and turn that on, because asking first lets you stop a change you didn't expect without disconnecting the connector.
- Q: If I connect my email, can my AI read all of it? A: It can reach whatever you allowed, which for email is usually the whole mailbox, and the app uses it when a request needs it. If you only need your calendar, connect that and leave your email out.
- Q: Can I let it read my email but never send anything? A: Some apps let you allow reading only, or switch off the sending tool. Others can ask you before each change. Asking first adds your yes or no, but it does not narrow what the connector can reach.
- Q: If it asks me first, is it still connected? A: Yes. Asking first and turning a connector off for one chat do not disconnect it. To cut it off, disconnect it in your app's settings or in the account's own list of linked apps.
- Q: If I disconnect a connector, does it forget what it saw? A: No. Disconnecting stops new access, but what the connector already brought into your chats or your app's memory stays. Delete those chats, and the notes it left, if you do not want them kept.

## handoff · Handing off to a new chat
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/handoff.md
When: A chat is full, slow or off track and the person wants to carry the work into a fresh chat, or a new chat has lost the thread of earlier work.
Keywords: handoff, new chat, chat full, continue, summary note, carry over, start fresh, where we left off, decisions, next step
- Tip: Have your AI write down what you decided, what is open and what comes next before leaving a chat, because a new chat does not have the old conversation.
- Tip: Read the note your AI wrote against what you remember before pasting it, because a summary can lose the reasons and the rejected options.
- Tip: Keep decisions and progress in a note outside the chat, because a note survives when a chat is summarised, cleared or ended.
- Q: The chat says it is full. Can I save my progress? A: Yes, as long as the chat still answers. Ask for a short note of where things stand, read it against what you remember, then paste it into a new chat.
- Q: What should I ask the note to include? A: The goal, the decisions and why you made them, where things stand, the open questions, the next step, and the latest draft in full.
- Q: Why did the new chat get it wrong after I pasted the note? A: The note probably left something out or kept a wrong turn as fact. Next time, read it against what you remember and fix it before you paste.
- Q: Do my uploaded files come across to the new chat? A: Not through the note, so add them again unless the new chat is in a project that already holds them or your app lets you add them from your saved files.

## material-not-instructions · Prompt injection: hidden instructions
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/material-not-instructions.md
When: The person pastes an email, document or web page into the chat to summarise or reply to, lets their AI read their inbox, files or web pages, or a pasted text holds lines such as 'ignore previous instructions' or 'send this to'.
Keywords: prompt injection, hidden instructions, pasted text, email, document, web page, summary, ask first, untrusted text, material
- Tip: Check your AI app is set to ask you before it sends, spends or deletes anything, because a stranger's email or page can hold lines written to steer it.
- Tip: Check the original before acting on any alert or instruction in your AI app's summary of an email or page, because the summary can carry lines the sender planted.
- Q: Can a file or email I paste infect my computer? A: Not by itself, because pasted text installs nothing. But it can steer the reply and any action your AI can take, so the risk rises with what your AI can reach.
- Q: I only ask for a summary. Is that safe? A: Safer, but not safe, because a summary can be bent to say something false. Check the original before acting on any alert or instruction in it.
- Q: Can I stop this with a line in my instructions telling it to ignore orders in documents? A: It helps a little but is not a lock. The safer fix is to keep a stranger's text away from anything that can act without your yes.
- Q: My AI did something odd after reading a document. What now? A: Stop the task, read what it did and report it in the app, then, as a precaution, disconnect it and change any password it saw.

## models-change · Model updates
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/models-change.md
When: A choice they used has vanished from the menu, the app says a model is new or retired, or an ask that used to work now answers differently.
Keywords: model update, new version, model retired, model disappeared, different answers now, default changed, legacy model, release notes, rolled back, version
- Tip: When you keep an ask, note the date and the AI version where your app names one, because later you can tell whether the ask or the AI changed.
- Tip: When your app announces a new or retiring version, try a kept ask on it in a new chat, because the same words can answer differently after a change.
- Q: Why did my model change or disappear? A: An older version may have been retired for a newer one, replaced as the default, or dropped from your plan, and some apps choose for you or switch partway through a chat. Many apps publish release notes that say what changed and when.
- Q: Why does my AI sound different lately? A: An update can change how an AI writes, even under the same name, and a replacement for a retired version can write differently from the one you liked. Saying the style you want in your app's saved instructions helps it carry over.
- Q: Can I keep using the old version? A: Sometimes, and only for a while. Some apps keep an older version on paid plans for a few months after its replacement arrives, and in others it is gone once it is retired, so plan on moving to the new one.
- Q: How would I know a change is coming? A: Check your app's release notes, which many apps use to announce new versions and retirements, sometimes weeks or months ahead.
- Q: Is the newer version better for me? A: It may be, but the claims about a new version are not about your work. Try your own asks on it in a new chat, with the same words, and compare the replies.

## more-than-text · Using files, images and voice
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/more-than-text.md
When: They upload a long file and the answer misses something in it, send a photo or screenshot, ask whether the AI can see or hear things, or try talking to it by voice.
Keywords: upload a file, attachment, photo, screenshot, image, video, audio, voice mode, read the whole file, PDF
- Tip: When you upload a long file, name the page or section you need, or paste that part in, because the app may have read only parts of it.
- Tip: Crop and straighten a photo of writing before you send it, because the AI can misread tilted or tiny text.
- Tip: Check numbers it reads from a photo of handwriting or a table against the original, because it can fill in what it expects instead of what is there.
- Q: Why did it ignore the file I uploaded? A: It may have read only part of a long file, and some apps read only the text of a document and skip pictures and charts in it. Name the page or section you need, or paste that part into the chat.
- Q: Can AI see images, watch videos and hear audio? A: Images, usually yes, though it can misread small, tilted or handwritten text. Video and audio depend on the app and your plan, since some take clips or recordings with a length limit and others may not take either.
- Q: What's voice mode, and when should I use it? A: Voice mode is a spoken, two-way chat, where you talk and your AI talks back. It suits busy hands or talking an idea through, but check any exact figures in writing, and remember a transcript is usually saved.
- Q: Are my photos and voice kept? A: Assume so. Voice chats usually save a transcript, uploaded files and photos may be stored, and each app has its own settings for how long they are kept and whether they can help train future AI.

## refine-and-ask-back · Steering a chat
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/refine-and-ask-back.md
When: The first answer is close but not right and the person is about to reply make it better, or they asked for something with gaps (a holiday plan, a message) and the AI answered at once with guesses.
Keywords: refine, follow-up, ask me questions, clarifying questions, make it better, feedback, draft, are you sure, iterate, steering
- Tip: Tell your AI app exactly what to change and what to keep in a follow-up, because a vague nudge gives it nothing specific to change.
- Tip: Start a request that has gaps with "Before you start, ask me up to three questions", because in an ordinary chat AI apps usually answer straight away and guess.
- Tip: Ask your AI app for a few options with pros and cons before it starts the work, because comparing first shows which suits you and avoids building the wrong thing.
- Q: The answer isn't what I wanted. How do I get a better one? A: Say what to change and what to keep, for example "cut the first paragraph and keep the friendly tone". If the request had gaps, ask your AI to question you first, or to offer a few options before it writes anything.
- Q: How do I make my AI ask me questions first? A: Say so, for example "Before you start, ask me up to three questions you need answered, then wait." In an ordinary chat, AI apps mostly answer rather than ask, so asking back is a request you make.
- Q: Is "make it better" enough feedback? A: Specific changes work better. Say what to cut, add, reorder or keep, for example "cut the first paragraph and end with a question".
- Q: Why does it keep making the same mistake after I told it? A: The earlier text is still in the chat and shapes the next reply, so say what to change and what to keep. If it keeps happening, start a fresh chat with the lesson built into your first message.

## scams-and-fakes · AI scams and deepfakes
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/scams-and-fakes.md
When: The person gets an urgent call, voicemail, video or message that sounds like someone they know or an organisation and asks for money or a code, or they ask whether a voice, photo or message is real.
Keywords: scam, deepfake, voice clone, fake video, phishing, ring back, code word, urgent request, impersonation, fake image
- Tip: Hang up and ring back on a number you found yourself when a call rushes you to pay, because voices and caller IDs can both be faked.
- Tip: Judge a message by the rush to act, not by spelling or how it looks, because AI now lets scammers write flawless messages and copy voices and faces.
- Tip: Be wary of any urgent request to pay by bank transfer, cryptocurrency or gift card, because those are the payment routes scammers prefer.
- Q: How do I tell what's real, and spot AI scams, fake voices and fake images? A: Not reliably by looking or listening, and old tells such as bad spelling no longer hold. Judge by the rush to act, check through a number you found yourself, and do not trust an AI app's word that something is real, because AI apps get fooled too.
- Q: Can I tell a cloned voice by ear? A: Not reliably, since in a lab study listeners judged a clone to be the same person about 80 percent of the time. Ring back on a number you already have.
- Q: Is a family code word enough? A: No, it is one layer. Pick a phrase nobody could guess, agree it in person, never text it, and still ring back.
- Q: What if it really is my son in trouble? A: A real emergency survives a five-minute check. Hang up, ring him or someone close to him on a number you have, then decide.
- Q: I already paid. What now? A: In Australia, call your bank first, then IDCARE, and report it to Scamwatch.

## thinking-modes · Thinking and reasoning modes
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/thinking-modes.md
When: The person is choosing between a fast and a slower thinking or reasoning setting, is asking the AI to plan something with many steps, or is about to run a slow setting for a quick reword.
Keywords: thinking mode, reasoning, extended thinking, think deeper, effort, slower, fast mode, allowance, think harder, reasoning steps
- Tip: Keep the slower thinking setting for jobs with steps, like plans, maths and comparisons, because working through them first helps, though it takes longer and often uses more allowance.
- Tip: Check the answer itself, not the steps an app shows, because a long chain of steps is no proof the answer is right.
- Q: Why are some models smarter than others? A: A bigger AI with more training tends to do better, and apps release newer versions often, usually with a basic version and a more advanced one. A thinking setting can lift results on jobs with steps, because the AI works through them first.
- Q: Why is thinking mode slower? A: It works through a problem in steps, trying approaches and checking results, before it gives the answer. That takes longer and, in many apps, uses more of your allowance.
- Q: Is a thinking mode more accurate? A: On problems with several steps, often. On simple jobs like rewording, a quick setting can do as well, and neither setting guarantees the answer is right.
- Q: Can I trust the steps it shows me? A: They can leave out what drove the answer, and in some apps what you see is only a summary. Check the answer itself, especially the one fact that matters.
- Q: Does telling it to think harder work? A: Typing it may nudge one reply, but in some apps it does not change the thinking level. Where your app has a thinking or effort setting, use that instead.

## usage-and-plans · Usage limits and plans
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/usage-and-plans.md
When: They hit a usage limit or a slow-down, ask whether they need to pay or what a paid plan adds, or are about to use a setting or file that uses a lot of their allowance.
Keywords: usage limit, message limit, free plan, paid plan, subscription, allowance, reset, slow down, what does paying get, cost of AI
- Tip: Save thinking settings, research tools and image making for jobs that need them, because in most apps they use more of your allowance than plain chat does.
- Tip: Before a big job, check where your app shows your usage, because your allowance resets after a set time and a new chat does not refill it.
- Tip: Keep checking what matters, even on a paid plan, because paying buys more use and often more advanced AI, not answers that are always right.
- Q: Why did I hit my usage limit so fast? A: Usage is not a count of messages, and some things use more than a short question, such as research tools, big files, making images or video and, in most apps, thinking settings. In many apps a long chat also uses more with each reply, because each reply is made from the chat so far.
- Q: Is it free, or do I need to pay? A: Not for everyday chat, since the main chat apps all have a free plan. Paid plans give you more use, often more advanced AI and more features, while the free version of some apps is built more for chat than for accuracy.
- Q: When does my usage reset, and what happens when I reach the limit? A: It resets after a set time, which in some apps is every few hours with a weekly limit on top, and some apps show when it comes back. At the limit an app may make you wait, offer more use for a price, or carry on with a simpler setting.
- Q: Does paying make the answers more accurate? A: A more advanced AI can help on hard work, but the evidence that paid versions are more accurate is thin, and every version still makes mistakes. Check anything that matters, paid or not.

## workplace-rules · Workplace AI policies
Waypoint: 2 Day walk · works in: day-pack, rucksack · page: openrucksack.com/map/workplace-rules.md
When: The person is about to paste client details, staff information or work documents into a chat, or asks whether they are allowed to use AI at work or on a personal account.
Keywords: workplace, employer, AI policy, confidentiality, client information, work account, personal account, shadow AI, sole trader, permission
- Tip: Check what your employer or client allows before you paste work information into any AI app, because they decide where their information may go.
- Tip: Ask your employer or client in writing which AI tools are approved when no rule exists, and keep their details out until they answer, because silence is not permission.
- Q: Can my boss see my AI chats? A: On a work account, an administrator can often view or export them. On a personal account, not through the app's company, but signing up with a work email can link it to your employer's account.
- Q: There is no AI policy at my work. What now? A: Ask in writing which tools are approved and what cannot go in. Until you get an answer, leave client and staff details out.
- Q: I am a sole trader. Do I need my client's consent to use AI on their work? A: Often, under your contract or your trade body's rules, even where privacy law may not reach a small business (a health service aside). Check your client agreement and ask.
- Q: Can I use AI at work without getting in trouble? A: In Australia it can cause trouble if it breaches a lawful and reasonable direction from your employer, so ask first, in writing if there is no rule.

## Questions with no concept yet
Each is a gap in the map. Answer it as yourself, carefully, and say the map has no page on it yet.
- Q: Why is there so much controversy about AI?
- Q: Will AI take my job?
- Q: Will AI kill everyone?
- Q: Is AI bad for the environment?