L
Month one · running it, not using it

Your first month with an AI tool

A hundred and thirty-seven habits for the point where you stop asking and start directing.

The rules, section by section

Before the rules

By the second month the tool stops being something you use and starts being something you direct, and the questions change with it.

Not how do I ask for this, but why does the default look like that, what is actually changing the answer, why does everything sound the same at volume, and which decisions should never leave your hands at all.

A hundred and thirty-seven habits. More than anyone reads at once, which is the point — this is the one you come back to rather than the one you finish.

A. Why its design output looks the way it does

Ask a model to design something and it produces the average of everything it has seen, which is why so much of it looks the same.

The layout arrives centred, with a gradient, rounded corners and three weights of the same typeface. Nothing is wrong with it. Nothing is chosen either.

Twenty-four habits about why the default looks the way it does, and what to say instead of make it look better.

A134 · What to do

Check the size of headings and spaces on a full page, not only on a small example, before you use the design.

Why

Models often make headings and spaces look good in small previews, but when the same style is used on a real page, everything grows too large. The result is a design that wastes space and looks odd.

What not to do

Don't trust how headings look in a sample box, because the same size will be overwhelming in a real report or dashboard.

Say it like this“Show me the full dashboard_report.pdf with smaller headings and tighter spaces.”
Not like this“Make headings look good in the preview.”
A135 · What to do

Set a clear maximum size for every heading, button, and text block before you finish the design.

Why

If you only say 'keep it small', the model might shrink things for now, but any update or change can make everything big again. A fixed maximum is easy to check and keeps things under control.

What not to do

Don't rely on reminders like 'keep it small', because those are forgotten and the next version might be huge again.

Say it like this“Limit title size to 32 pixels in the Q2_review.pptx slides.”
Not like this“Make the titles smaller, please.”
A136 · What to do

Check how much space each layer of boxes or containers adds up to, not only the space inside one box.

Why

Each container adds its own padding or margin. When several are nested, the space multiplies, and you end up with big gaps you did not plan for. The total can be hundreds of wasted pixels.

What not to do

Don't look at only the space in one container, because the layers together can add up to much more than you expect.

Say it like this“Show all padding and margin layers in the finance_summary.html layout.”
Not like this“Reduce the padding in the main box.”
A137 · What to do

Check the contrast of every bit of text, especially grey text, before you use a design from a model.

Why

Models often use low-contrast grey text because it looks stylish in isolation. On a real page, though, this is hard to read for most people, especially in poor lighting or on older screens.

What not to do

Don't accept grey text that looks good in a preview, because on a real page, many people will struggle to read it.

Say it like this“Increase contrast for all grey text in the onboarding_email.docx.”
Not like this“Use a lighter grey for secondary text.”
A138 · What to do

Choose the text colour based on the background colour, not personal taste, every time you design a page.

Why

Background colour affects how readable the text is. If you pick a text colour because you like it, without checking the combination, you can end up with unreadable or ugly results.

What not to do

Don't pick a text colour because it looks nice in isolation, because it might clash or disappear on your actual background.

Say it like this“Match text colour to the blue background in the schedule_2024.xlsx sheet.”
Not like this“Use my favourite grey for all text.”
A139 · What to do

Make important words stand out by using size or bold, not by fading other text.

Why

Fading text makes it hard to read, especially for people with less sharp eyesight or in dim rooms. Important information can disappear, so nobody notices it when they need to.

What not to do

Don't use faded or light text to make other words stand out, because faded text is often missed or unreadable.

Say it like this“Bold the key dates in the project_milestones.docx instead of fading others.”
Not like this“Fade the less important text.”
A140 · What to do

Click every button in the design, checking how each one looks and works when resting, hovered over, clicked, or disabled.

Why

Buttons can change or even disappear depending on their state. Hovering or disabling can make a button fade, lose contrast, or become invisible, which leaves you unable to use or even find it.

What not to do

Don't check buttons only when they are active. Ignoring hover or disabled states means you might miss when a button disappears or stops working for someone.

Say it like this“Show me 'Submit' in all states in Invoice_2024-06-12.fig.”
Not like this“Check the Submit button.”
A141 · What to do

Use only style names that have been set and checked in the design system, so the tool can apply them correctly.

Why

A style name not set anywhere can make text vanish. For example, white text on a white background disappears without warning, because the tool cannot find a matching style to use.

What not to do

Don't type in style names that aren't set up. Guessing or inventing a style name can make your text invisible or look broken.

Say it like this“Apply 'Button/Primary' style from the approved list to Save_Button.fig.”
Not like this“Use a new style called 'BrightText'.”
A142 · What to do

Check which style settings are already applied to your design before adding new colours, borders, or shapes.

Why

Adding a new colour or shape that does not match the current ones makes the design look like it belongs to another app. The mismatch stands out and confuses people.

What not to do

Don't add a new style before checking what's already set. Ignoring existing settings can lead to clashing looks and a messy page.

Say it like this“Before changing the border on Profile_Card.fig, check its current style.”
Not like this“Add a new border style to the card.”
A143 · What to do

Pick a colour already in use in the design when you need a new one, instead of adding a new shade.

Why

A single new shade stands out as a mistake. People spot an odd colour within seconds, because it breaks the visual pattern set by the rest of the design.

What not to do

Don't add a fresh colour unless it matches one already used. A lone shade looks like an error and draws the eye for the wrong reason.

Say it like this“Use the existing blue from Header_2024.fig for the new button.”
Not like this“Add a lighter blue to the new button.”
A144 · What to do

Check which styles are linked to a main colour before changing it, as the change will affect all connected headings and links.

Why

Changing a root colour silently updates every style linked to it. All headings, links, and buttons using that style will change at once, even if you wanted to fix only one part.

What not to do

Don't change the main colour without checking what else uses it. You might fix one problem but break everything that shares the same style.

Say it like this“Before editing Primary_Red in HomePage_2024.fig, see which components use it.”
Not like this“Change the main red to orange.”
A145 · What to do

Choose a single colour family to use on each page, and remove any colours that do not belong to that group.

Why

Three bright colours on the same page compete for attention. The page looks unfinished and scattered. Sticking to one colour family makes the design calm and easy to follow.

What not to do

Don't mix many colour families on a page. Using several bright colours together makes everything shout for attention and nothing feels settled.

Say it like this“Keep only the green shades in Dashboard_Q2.fig and remove the orange and purple.”
Not like this“Add a red button to the green and purple page.”
A146 · What to do

Keep important text in a neutral colour, and use colour only for details such as links, navigation crumbs, or highlights that show structure.

Why

Bright colours on main text or links pull your eyes away from what you came to read. Coloured tabs or focus rings, though, help you see where you are without making the main content harder to follow.

What not to do

Don't colour all your links, headings, and main text. When every word stands out, you lose track of what matters and where you are on the page.

Say it like this“Keep the main text in grey for Q2_report.html, colour the sidebar links.”
Not like this“Make all links and headings blue in Q2_report.html.”
A147 · What to do

Make each button fit the length of its label, and arrange buttons in rows that wrap, not stretched across the page.

Why

Buttons that fill the whole column look like someone rushed through a form layout. Rows of right-sized buttons look more deliberate, and help people spot what to click without guessing.

What not to do

Don't make every button as wide as the screen. People will think the layout is unfinished, and it becomes harder to see which button does what.

Say it like this“Set the 'Send' and 'Cancel' buttons for invoice_2024.pdf to fit their words.”
Not like this“Make the 'Send' and 'Cancel' buttons full width on invoice_2024.pdf.”
A148 · What to do

Use vector icons, such as SVGs, inside shapes for buttons or labels, instead of using text symbols like arrows or stars.

Why

Text symbols shift position on different browsers and devices, making it hard to centre them. Fixing those tiny shifts can take hours, especially when a project is nearly finished.

What not to do

Putting text arrows or stars in buttons makes buttons look off-centre on some screens, and you might spend hours fixing alignment. A quick fix seems tempting, but icons or plain text work better in practice.

Say it like this“Add an SVG arrow icon to the 'Next' button in leave_form.docx.”
Not like this“Put a '>' symbol in the 'Next' button on leave_form.docx.”
A149 · What to do

Check generated pages for repeated but slightly different style values, such as button curve, card spacing, or colours, across many files.

Why

One project ended up with three different button curve sizes, four card spacings, and over 150 colours. No one chose these on purpose; they appeared as new files were added and copied.

What not to do

Ignoring small differences in style values between files adds up, making your pages inconsistent and harder to maintain. It's easy to overlook minor changes, but they combine to create bigger problems.

Say it like this“List all the button and card styles in the onboarding_dashboard.html project.”
Not like this“Let each page in onboarding_dashboard.html use its own button style.”
A150 · What to do

Fix style drift by looking up and reusing old style values, not by adding new rules meant to be 'consistent'.

Why

Adding a new rule for consistency, without checking what already exists, caused bugs in almost every file. Many went unnoticed, because no one opened all the files to see the problems.

What not to do

Don't add new CSS rules for consistency without checking old ones. You might break layouts or cause hidden bugs in files you never open.

Say it like this“Check the existing button styles in HR_portal.css before changing the curve.”
Not like this“Add a new button curve rule to HR_portal.css for consistency.”
A151 · What to do

Use fewer decorative elements and colours, especially on design pages, to show you understand what matters.

Why

When every part of a page is decorated, nothing stands out. People often think too much colour or decoration means the designer is inexperienced, especially when showing off design work.

What not to do

Don't add lots of colours, gradients, or borders to show skill. Too much makes your work look cluttered and less professional.

Say it like this“Keep the layout for design_review_23.html simple, with one accent colour.”
Not like this“Add gradients and borders everywhere in design_review_23.html.”
A152 · What to do

Write numbers in plain text, without making them bold, so the natural contrast with words does the work.

Why

Numbers already catch the eye because they look different from words. Making them bold removes this natural difference, so numbers blend in with headings or labels and lose their quick impact.

What not to do

Highlighting numbers by making them bold makes them harder to spot and the page look noisy. You might think bold stands out, but it blends numbers into other bold text and distracts from key figures.

Say it like this“Show 15 overdue reports in the summary for Ramesh.”
Not like this“Highlight 15 in bold in the summary for Ramesh.”
A153 · What to do

Add a label only when the content would be confusing or ambiguous without it; avoid stacking labels before the main information.

Why

Too many labels before the real content slow people down. Readers start to ignore them, or worse, miss what matters. Labels should help, not create clutter or pretend to organise when they do not.

What not to do

Labelling every single section, field, or button makes the screen feel heavy and hides what matters. Adding too many labels might seem helpful, but it drowns out the important ones users need to see.

Say it like this“Label the 'Deadline' field in the Priya_Quarterly_Report.xlsx upload form.”
Not like this“Add labels to every field in the Priya_Quarterly_Report.xlsx form.”
A154 · What to do

Design buttons and controls that are used many times a day to be quiet and subtle, so they do not distract from the main task.

Why

Obvious or brightly coloured buttons everywhere make it hard to focus. When the most-used controls fade into the background, people can work faster without being distracted by constant visual noise.

What not to do

Making every frequently used button bright or large makes the screen busy and slows down finding what matters. Highlighting only the key actions helps users spot the right button quickly.

Say it like this“Make the 'Save' button in the Raj_Sales_Pitch.docx editor a subtle grey.”
Not like this“Make the 'Save' button in Raj_Sales_Pitch.docx bright blue.”
A155 · What to do

Design important actions so they are clear and easy to use, not by making them the biggest or loudest thing on the screen.

Why

People trust actions that are easy to find and use, not ones that shout for attention. Size and colour can make something look risky or pushy, which makes people hesitate or miss it entirely.

What not to do

A huge and red 'Submit' button for the payroll form draws too much attention and can make the action seem risky, which distracts people from their regular work and may cause hesitation.

Say it like this“Place the 'Submit' button for Payroll_March.csv in a clear spot, easy to reach.”
Not like this“Make the 'Submit' button for Payroll_March.csv extra large and red.”
A156 · What to do

Try all possible options for a setting before adding a control, to check if changing it actually helps or alters the result.

Why

Some settings sound useful but only add confusion. If changing the setting never improves the outcome, a control wastes space and time. Only real testing shows which options are worth exposing.

What not to do

Adding a slider for every possible setting in the image export for Asha_Presentation_2024.pdf can tempt you with flexibility, but too many sliders make the tool confusing and slow to use in real work.

Say it like this“Test all image quality levels before adding a control to Asha_Presentation_2024.pdf export.”
Not like this“Add a control for every export setting in Asha_Presentation_2024.pdf.”
A157 · What to do

Avoid setting a fixed lowest value for a setting unless there is a clear best minimum; leave the range open if no one value works for everyone.

Why

A hard minimum blocks people from choosing what works for their situation. If there is no obvious best lowest value, setting a limit is one person's guess, which can stop better results.

What not to do

Setting the minimum font size in the Anil_Invoice_Template.docx to 12 may seem like a safe default, but some users need it smaller, so a strict limit blocks valid use cases and causes frustration.

Say it like this“Let the font size in Anil_Invoice_Template.docx go below 12 if needed.”
Not like this“Set the minimum font size in Anil_Invoice_Template.docx to 12.”

Try these — why its design output looks the way it does

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

B. Layout, phones, and what fits on a screen

A screen is a hard constraint and a model has never held a phone.

The design reads beautifully in the reply and breaks at 390 pixels, because nothing in the conversation ever mentioned that most of the people reading it are on a phone in a corridor.

Twenty-four habits about what actually fits, what a thumb can reach, and why the mobile version is the design rather than a version of it.

B158 · What to do

Put all layout rules for mobile and desktop together in one CSS file, so you update and check everything in one place.

Why

When layout rules live in separate files, changes in one are often forgotten in the other. Over time, layouts no longer match. Mistakes double, and you spend extra time fixing the same bug twice.

What not to do

Don't split mobile and desktop layout rules into two files. Updates in one file often get missed in the other, so layouts drift apart and bugs multiply.

Say it like this“Add both mobile and desktop rules to style-main.css.”
Not like this“Make a separate CSS file for mobile layout.”
B159 · What to do

Store colour and font rules in their own section or file, separate from size and position rules for each layout group.

Why

Colour and font choices should look the same everywhere, but layout changes by screen size. Mixing them means a change for one device accidentally changes others, making appearances inconsistent.

What not to do

Don't mix colour and font rules with layout rules for each screen size. If you do, a font or colour tweak for one device can break how it looks on every other.

Say it like this“Keep colours and fonts in variables.css, layouts in style-main.css.”
Not like this“Put all rules, including fonts and colours, in one CSS block.”
B160 · What to do

Show the same web page regardless of whether someone uses a phone, tablet, or computer, and switch layout based on the screen size, not the device.

Why

Device type is unreliable because screens can be resized, rotated, or misidentified. Guessing device type leads to the wrong layout showing up on tablets, odd windows, or phones in landscape.

What not to do

Don't serve different pages or layouts by checking the device type. Devices change shape, and pages will appear wrong when someone rotates or resizes their screen.

Say it like this“Use media queries in index.html to adjust layout for all devices.”
Not like this“Detect device type and show a separate mobile page.”
B161 · What to do

Decide which elements shrink, move, or hide when designing for phones; don’t only scale down the desktop layout.

Why

Shrinking everything makes buttons too small, text unreadable, and controls overlap. Without clear rules for what changes, mobile layouts become crowded and hard to use.

What not to do

Don't treat mobile layout as a smaller version of desktop. If you do, controls will crowd together, and users will struggle to tap or read anything.

Say it like this“Hide the sidebar and stack buttons in mobile-view.css.”
Not like this“Scale all elements down for mobile.”
B162 · What to do

Test your layout in narrow windows and on phones yourself, not only on a big screen, to catch broken layouts.

Why

Desktop layouts can pass all checks while mobile layouts break. Narrow screens often show issues like sideways scrolling, cut-off text, or images that don’t fit, which go unnoticed unless you look.

What not to do

Don't assume a layout that works on desktop is fine on mobile. Many problems only show up when you test in a small window or on an actual phone.

Say it like this“Check the contact page on a phone and a laptop.”
Not like this“Approve layout after checking only on desktop.”
B163 · What to do

Use the viewport unit that updates as the visible screen changes, so layouts adapt when toolbars or address bars appear or disappear.

Why

Old viewport units guess the screen size and ignore browser bars. When toolbars show or hide, layouts overflow or leave gaps, especially on mobile browsers, making pages look broken.

What not to do

Don't use old viewport units like 100vh for mobile layouts. Toolbars can appear, causing the layout to overflow or hide content behind the address bar.

Say it like this“Set hero section height with 100dvh in home.css.”
Not like this“Set section height to 100vh for all screens.”
B164 · What to do

Add up the height of every part—headers, footers, toolbars, and content—before starting to arrange your layout on a phone screen.

Why

Layouts break when the total height of all parts is more than the screen allows. People often miss a small piece, like a filter bar, and only notice after hours of shifting things around.

What not to do

Don't guess or eyeball the sizes for each section, because missing even 10 pixels can push key controls offscreen and waste hours later.

Say it like this“Sum header, footer, and content heights before designing the layout for invoice-review.pdf.”
Not like this“Start building and fix the layout if something doesn’t fit.”
B165 · What to do

Arrange every control—buttons, fields, and menus—so you can reach them all without scrolling, even on a small phone.

Why

Hiding controls below the fold means people miss them, especially when in a hurry. On phones, scrolling for a button leads to mistakes and support calls about missing features.

What not to do

Don't tuck important buttons or fields below a scroll area, since people will not know to look there and could miss deadlines.

Say it like this“Move the Submit and Cancel buttons for leave-form.docx above the scroll area.”
Not like this“Hide the Save button at the bottom; people can scroll if needed.”
B166 · What to do

Check that the whole page fits on the screen when no scrollbar is visible, instead of assuming hidden scrollbars mean nothing is cut off.

Why

Some browsers or devices hide scrollbars by default, so content can spill offscreen without any sign. People then cannot reach hidden information, like Ajay missing the last step in a checklist.

What not to do

Don't assume a missing scrollbar means everything fits. Content might be cut off and unreachable, causing confusion and missed actions.

Say it like this“Test the weekly-tasks.html page on iPhone and Android to make sure nothing is hidden.”
Not like this“No scrollbar shows, so the checklist must fit fine.”
B167 · What to do

Adjust the part that sticks out past the screen, such as a table or image, instead of shrinking the area that contains it.

Why

Shrinking the container hides whatever sticks out, like a Submit button below a data grid. The top might look fine, but key actions disappear, causing people to get stuck.

What not to do

Don't reduce the container size to hide overflow, since that buries important controls and makes them impossible to reach.

Say it like this“Resize the chart in Q2-report.xlsx so it fits inside the panel.”
Not like this“Cut the panel height to hide the chart overflow.”
B168 · What to do

Keep the container’s height steady, even when items like messages or alerts appear or disappear, so the rest of the screen does not jump around.

Why

When a container’s height changes, the layout shifts and people lose their place. For example, a warning message in the leave-approval form made the whole screen jump, causing Priya to click the wrong button.

What not to do

Don't let the container resize itself every time a message pops in or out, since that makes the screen jump and confuses people.

Say it like this“Reserve space for alerts in the leave-approval-form.pdf so the layout stays stable.”
Not like this“Let the container grow when an error message shows.”
B169 · What to do

Leave enough space for anything fixed to the screen edge, like a chat bar or notification banner, so it never covers up content underneath.

Why

Edge-fixed items overlap content and hide parts of the page. For weeks, a settings section stayed hidden behind the always-on chat bubble in payroll-summary.docx, leading to repeated complaints.

What not to do

Don't let fixed-edge controls overlap the main content, or people will miss important sections and get frustrated.

Say it like this“Shift the payroll-summary.docx content down to make room for the chat bar.”
Not like this“Leave the chat bubble floating over the settings section.”
B170 · What to do

Set up sliding panels so they hover over your main content, without pushing or shrinking anything else on the screen.

Why

A sliding panel that takes up layout space will squeeze lists, tables, or forms, making text unreadable and buttons hard to reach. The main area warps or jumps, which confuses people and disrupts their work.

What not to do

A sliding panel that moves the rest of the page aside often breaks the layout, especially on small screens, so people end up with cramped content and a harder time finding what they need.

Say it like this“Show the filters-panel over dashboard-summary.xlsx without resizing the table.”
Not like this“Open the side panel and move the dashboard to the right.”
B171 · What to do

Give each parent container control over which child elements—like sticky bars or dropdown menus—should appear above or below others on the screen.

Why

Dropdown menus or pop-outs can get trapped behind sticky headers or footers if you do not set the right order. People cannot see options, so they miss choices or make mistakes.

What not to do

Sticky bars or floating buttons that can appear anywhere might seem convenient, but they sometimes cover pop-up menus or important controls, making it difficult for people to click or finish their tasks.

Say it like this“Make sure Priya's dropdown in the sticky-navbar sits above the project-tabs.”
Not like this“Let the dropdown open wherever its default setting puts it.”
B172 · What to do

Place any third-party widget, such as a map or text editor, inside its own layer group so it cannot cover up your pop-ups or other panels.

Why

External widgets sometimes ignore your site’s order of layers. A map or embedded editor can end up on top, blocking pop-ups or dialogs that need attention, so people cannot finish their tasks.

What not to do

Adding a map or editor straight into the main layout might feel efficient, but these can spill over other content, hiding menus or dialogs right when you need them most during your work.

Say it like this“Put the Google Maps widget for office-locations.csv inside its own layer box.”
Not like this“Drop the map into the page with no layer control.”
B173 · What to do

Use your own tooltip system for hints and help, instead of letting widgets show their built-in tooltips.

Why

Built-in tooltips from widgets usually stick to the browser window, not your page layout. When you have a fixed header or sidebar, the tooltip can get stuck behind it and people never see the help.

What not to do

Leaving the widget's default tooltip enabled can hide help text behind fixed headers or navigation bars, which means nobody finds the help they need when using your tool.

Say it like this“Replace the editor's tooltip in report-2024.docx with our site tooltip.”
Not like this“Keep the default tooltip from the editor plugin.”
B174 · What to do

Change only the visibility of list items as someone types or filters, instead of rebuilding the whole list structure on every keystroke.

Why

Rebuilding a long list with every letter typed makes the page flicker and resets scroll position. People lose their place, and the screen jumps, which slows down work and causes mistakes.

What not to do

Refreshing or rebuilding the full list after every key press might seem responsive, but it causes the screen to flash and makes people lose their place, forcing them to scroll back repeatedly.

Say it like this“Hide rows in invoice-list.xlsx as Amita types, but keep the scroll steady.”
Not like this“Rebuild the invoice list every time Amita types a letter.”
B175 · What to do

Always set the scroll position to the top when showing a reused page or panel, so people start from the beginning of the content.

Why

If a panel or page is reused and keeps the last scroll position, the next person may land in the middle or end of the content, which looks broken and makes it hard to find what is needed.

What not to do

Letting a reused panel open at the last scroll position confuses people, as it appears that content is missing or has been cut off, which can slow down their work.

Say it like this“Reset scroll to the top when showing the employee-details panel for Rajesh.”
Not like this“Show the panel at whatever scroll it had last time.”
B176 · What to do

Apply animation transitions only to the panel or area that is opening, not to both open and close states at the same time.

Why

Animating both the opening and closing panels together causes them to overlap for a point. People see two panels at once, which looks confusing and makes it unclear which one is active.

What not to do

Don't animate both the panel that is opening and the one that is closing. Overlapping panels for even a second can make people think something is broken.

Say it like this“Animate the transition only when side-panel-contacts opens, not when it closes.”
Not like this“Animate both panels when switching from contacts to messages.”
B177 · What to do

Stop any timers or animation effects as soon as a view or panel is closed, so nothing keeps running in the background.

Why

If a timer or animation keeps running after a view closes, it can move things around unexpectedly. Someone may have already moved on, so the page can shift and confuse them.

What not to do

Don't let a loading spinner or animation keep running after closing the settings window. Background movement can shift the layout and distract people who are working elsewhere.

Say it like this“Clear the countdown timer when the dashboard view closes for Priya's report.”
Not like this“Let all animations finish even after the user leaves the page.”
B178 · What to do

Show a placeholder shape that matches the real content while data is loading, instead of a blank screen or the word 'Loading'.

Why

A blank page looks like a mistake or an empty screen. Showing a shape that matches the real content tells people something is coming and helps them recognise the layout.

What not to do

Don't show a white screen or a line saying 'Loading...' when waiting for the sales chart. People might think the page is broken or has nothing to show.

Say it like this“Display grey boxes shaped like the real cards while summary-data.csv loads.”
Not like this“Show 'Loading...' until the dashboard appears.”
B179 · What to do

Size cards, boxes, or content areas based on the largest real data items you have, not on guesses or samples.

Why

If you guess sizes, long titles or descriptions can get cut off when the page goes live. Real data shows the biggest case, so nothing gets hidden or looks broken.

What not to do

Don't set card sizes based on short test names. Real entries like 'Quarterly Revenue Breakdown: Marketing and Partnerships' might get cut off.

Say it like this“Make the card for project-brief.pdf wide enough for the longest title in the list.”
Not like this“Guess the card size from the first few items only.”
B180 · What to do

Give more space to the main content than to the page or section title, so people can read what matters most.

Why

People come for the main text, not the label. If the title takes up too much space, the content feels cramped and harder to read.

What not to do

Don't make the title of the 'Weekly Update' section bigger than the actual notes from Farhan. People need space to read the details.

Say it like this“Let the notes in team-update.docx take up more room than the header.”
Not like this“Make the title bar larger than the content area.”
B181 · What to do

Arrange important content so something useful always appears first, not empty space or blank areas at the top of the screen.

Why

If the first thing people see is empty space, they may think nothing is happening and stop looking. Useful content at the top keeps attention and helps people find what they need.

What not to do

Don't leave a big gap at the top of the report page. People might close it before they see the summary below.

Say it like this“Show the summary for sales-report-2024.pdf at the top, not halfway down.”
Not like this“Leave a blank area above the main content.”

Try these — layout, phones, and what fits on a screen

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

C. How asking really works

By the second month the interesting question stops being how to ask and becomes what asking is doing.

The same request, sent twice, comes back differently. Not because the tool is unreliable, but because one version carried the situation and the other carried only the task.

Twenty-nine habits about the machinery underneath: what changes an answer, what only changes its length, and where the specification actually lives.

C182 · What to do

Set up the AI tool's controls or settings to limit what the AI can say, instead of asking for limits in your message.

Why

AI tools ignore instructions hidden in the message, like 'only show code.' The system always adds some explanation or greeting, even if you ask for code only. Controls work, messages do not.

What not to do

Don't write 'Only give me the code' in your prompt. The AI will still add extra words, so your output will not match what you want.

Say it like this“Show only the SQL code needed for sales_report_2024.csv.”
Not like this“Only reply with code, no explanation.”
C183 · What to do

Check the form and format of your data before you show it to anyone or save it, making sure it matches exactly what you need.

Why

Looking for a marker, like a tag, can let through long explanations that mention the tag but do not actually contain the correct data. Format checks block these mistakes.

What not to do

Don't look for a keyword or a tag in the AI's answer and assume the data is ready. You might end up displaying a long paragraph instead of the actual data.

Say it like this“Display the cleaned email addresses from contacts_list.xlsx only if they match the email format.”
Not like this“Show any answer that mentions 'email addresses.'”
C184 · What to do

Keep any internal notes or plans the AI creates fully hidden from the user's screen, so only the final answer appears.

Why

One time, the AI's planning notes were shown to everyone. The page filled with steps and drafts nobody needed, which confused the team and wasted time.

What not to do

Don't display the AI's full internal thought process or planning steps. Users will see pages of confusing information they never asked for.

Say it like this“Show only the final summary for the Q2_report.docx review.”
Not like this“Display the AI's full plan for writing the summary.”
C185 · What to do

Show only error messages written by a person to users, never the raw error text made by the AI.

Why

AI-generated error messages are often unclear or too simple, turning into one line that does not help. People need clear, useful messages, so use ones written by someone, not the AI.

What not to do

Don't let the AI's error messages appear on the user's page. Most are too vague or unhelpful, causing confusion instead of solving the problem.

Say it like this“Show 'File upload failed. Please try again.' if the AI cannot process data.csv.”
Not like this“Show 'An error occurred, please check your input.'”
C186 · What to do

List every possible result the AI might give before you start, including all final answers and known errors.

Why

If you do not know every result, unexpected answers or failures can slip through. You might get something you did not plan for, which could leak onto the page.

What not to do

Don't start without writing down every output the AI could give. Missing one means you risk showing or saving something you did not expect.

Say it like this“Prepare for 'report ready,' 'file missing,' or 'data error' from the AI for monthly_budget.xlsx.”
Not like this“Ask the AI for the budget and handle whatever comes back.”
C187 · What to do

Make sure the checks on what you send to the AI and what you accept back match exactly, so no answer slips through the cracks.

Why

If the rules for sending and receiving are different, you get answers that can show up but never save, or junk that saves but never appears. Both break the process.

What not to do

Don't use different checks for sending and receiving data. Mismatched rules mean you lose or wrongly keep information, causing errors in your workflow.

Say it like this“Use the same format check for both uploading and displaying team_schedule_15.docx.”
Not like this“Check file type on upload, but not when showing the file.”
C188 · What to do

Delete information from your saved records after you make a big mistake, like uploading the wrong version of Q2_Report_2024.xlsx.

Why

Any error you leave in your saved data will keep showing up in future results. Fixing settings or checks only helps new work, not what you already stored by mistake.

What not to do

Don't assume correcting your prompt or settings will clean up old errors. Past mistakes remain in your files and can be used again without you noticing.

Say it like this“Remove all entries from April in Q2_Report_2024.xlsx after the formula error.”
Not like this“Update the formula and keep using the same report.”
C189 · What to do

Describe how you want your answer to feel or behave, not the exact words you want to appear in the answer.

Why

Mentioning a word in your instructions puts it in the system's memory, so the tool often repeats it. Repetition makes answers sound forced or artificial, which is not how people really work.

What not to do

Telling the tool to use a specific word if you care about tone or mood can trap the answer into echoing your instruction, rather than producing a reply that matches your actual goal.

Say it like this“Make the summary for ClientUpdate.txt sound urgent but polite.”
Not like this“Use the word 'urgent' in your reply.”
C190 · What to do

Avoid using broad or common phrases in your instructions, because they make answers too general.

Why

Using fixed phrases leads the system to pull from average, bland examples, so the answers miss your specific situation and sound like every other reply, which is tempting but not helpful.

What not to do

Adding words like 'best practice' or 'innovative solution' to your prompt can make the answer generic, which may seem safe but offers little help for your real work.

Say it like this“Explain the steps we took in BudgetReview.docx for the audit.”
Not like this“Give me best practices for budget reviews.”
C191 · What to do

Stop using overused words in your file names, task names, and variable names, not only in your instructions.

Why

Every name you give a file or task shapes what the system writes next. If you use tired words, the system keeps repeating them, making your work less clear and more repetitive.

What not to do

Don't rename a task to 'Innovative_Strategy' and expect fresh ideas. The system will keep using the same language and patterns in its replies.

Say it like this“Rename Plan2024.docx to Q2_ResourcePlan.docx so the name says what it is.”
Not like this“Call the file Best_Practices_Plan.docx.”
C192 · What to do

After banning an overused word, check your whole list for similar words before you write again.

Why

Banning a tired word often leads your mind to pick a synonym without realising it. You might think you have fixed the problem, but the same dull pattern keeps slipping into your files and answers, even after the ban.

What not to do

Don't swap 'effective' for 'efficient' and move on. Both are overused, and your answers will still sound generic.

Say it like this“After removing 'innovative', also check for 'cutting-edge' in the project summary for Rahul.”
Not like this“Replace 'innovative' with 'creative' and send it.”
C193 · What to do

Limit the words you use, but keep the topic the same. Don't change what you are asking about.

Why

Choosing different words is a skill. If you change the topic to avoid a banned word, you stop solving the real problem and miss what your task needs.

What not to do

Don't avoid writing about risk in RiskRegister2024.xlsx by switching to another subject. You need to address the real topic, with better words.

Say it like this“Write about project risks for RiskRegister2024.xlsx without using 'challenge' or 'issue'.”
Not like this“Skip the risk section to avoid overused words.”
C194 · What to do

Write any limits or restrictions at the end of your prompt, and tag them as never to say or do.

Why

Systems process instructions in order, giving the end the most weight. Limits buried in the middle often get ignored, so putting them last ensures the system remembers and follows them.

What not to do

Don't put your never-to-say list or limits in the middle of your prompt, as the system may miss or override them by later instructions.

Say it like this“Summarise the report, then at the end, never say 'draft' or 'in progress'.”
Not like this“Never say 'draft' in the summary above.”
C195 · What to do

Keep instructions short and clear, since long prompts hide important details in the middle.

Why

Long instructions cause the system to focus on the beginning and end, often missing or misapplying details in the middle. Short, direct prompts make each rule more likely to be followed.

What not to do

Don't write a long block of instructions with important rules in the middle, as those are likely to be skipped or misread by the system.

Say it like this“List steps for the invoice, each as a short line, not a paragraph.”
Not like this“Write all invoice steps in one big paragraph.”
C196 · What to do

If you have a condition, write two separate prompts and choose one before you start.

Why

Conditional statements like 'if this, then that' get confused with similar words or partial matches, leading to ignored or misapplied instructions. Deciding which prompt to use before asking avoids this problem.

What not to do

Don't include soft if-then statements in your prompt, as the system may not handle them correctly or may mix up the conditions.

Say it like this“Write a summary for report_2023.pdf. If it’s over 10 pages, use this prompt instead.”
Not like this“Summarise report_2023.pdf if it’s short, otherwise give a detailed summary.”
C197 · What to do

Write a separate prompt for each task, instead of combining all instructions into one.

Why

Combining tasks in one prompt causes instructions to overlap and conflict, making it hard for the system to follow each rule. Separate prompts keep tasks clear and prevent confusion.

What not to do

Don't ask for everything in one prompt, as it creates conflicts and muddled results.

Say it like this“First, summarise the meeting notes. Next, list action items in a new prompt.”
Not like this“Summarise the meeting notes and list action items in one go.”
C198 · What to do

Ask for each item separately with a simple, direct request. Don’t add more rules to try to get variety.

Why

Adding more rules makes the system follow a new, blended pattern, not more variety. Short, focused requests for each item create more natural and different responses.

What not to do

Don't pile on extra rules hoping for variety, as the system will create a new, repetitive style instead.

Say it like this“Write a summary for task_7.docx. Then, in a new prompt, write a summary for task_8.docx.”
Not like this“Summarise task_7.docx and task_8.docx with lots of variety.”
C199 · What to do

Show real examples from actual work, like a file or conversation, instead of describing what to do in general terms.

Why

The system learns best by copying real moments. Vague or general instructions lead to bland, repetitive results. Real examples show exactly how to act in practical situations.

What not to do

Don't explain the task in the abstract or with made-up situations, as this leads to generic, lifeless answers.

Say it like this“Rewrite the email Priya sent about the Q2 deadline, keeping her style.”
Not like this“Rewrite a typical deadline email in the same style.”
C200 · What to do

Give two clear, detailed examples of your answer using real files or tasks, not more or less.

Why

When you see only two examples, your mind can compare them and notice the style. More than two makes it hard to keep track, and the main point gets lost in the crowd.

What not to do

Don't add four or five examples thinking more is better. Too many examples blur the pattern, and you end up copying the wrong parts or missing the main idea.

Say it like this“Show two sample emails using the Q1_Report.docx deadline.”
Not like this“Give several examples of a project update email.”
C201 · What to do

Check every example for mistakes before sharing, and leave out any you are not sure about.

Why

Mistakes in examples get copied into your own work, even if you know better. A bad example sticks in your mind, and you repeat the error without noticing.

What not to do

Don't include an example you think is 'close enough' or 'probably fine.' Even a small error will be repeated, and you will end up fixing the same mistake later.

Say it like this“Give one correct summary using the notes from Ravi's meeting.”
Not like this“Share a draft summary, even if it might have errors.”
C202 · What to do

Ask for the finished answer first, then ask for the steps or explanation after.

Why

When you see the final answer before the steps, you know if it fits your needs. If you ask for the process first, you might get lost in details, and the answer could drift away from your goal.

What not to do

Don't ask for the steps before you see the answer. Starting with the process makes it easier to lose track of what you needed, and the reply can go off course.

Say it like this“Show the summary for Budget2023.xlsx, then list your steps.”
Not like this“Explain how you would summarise Budget2023.xlsx.”
C203 · What to do

Ask the tool to show its thinking or calculation, especially if you need high accuracy.

Why

If you only see the answer, you cannot check how it got there. When the tool explains its thinking, you can spot mistakes or steps that do not fit your needs.

What not to do

Don't hide the steps by asking for only the result. If the answer is wrong, you will not know where it went off track, and fixing it takes longer.

Say it like this“Show your steps for the totals in Sales_Results_May.csv.”
Not like this“Give the final sales total for Sales_Results_May.csv.”
C204 · What to do

Tell the tool to check its answer against your rules or criteria, and show the check out loud.

Why

When the tool reviews its own answer, it often catches mistakes before you see them. Hearing the check helps you spot anything missed, and you can trust the result more.

What not to do

Don't skip the review step. If you only look at the answer, you might miss errors that the tool could have caught by checking its own work.

Say it like this“Check your reply to the five points in the Meeting_Minutes_14June.txt.”
Not like this“Summarise Meeting_Minutes_14June.txt.”
C205 · What to do

State the exact number of items you want in each list or slot, and match it to your template.

Why

If you do not say how many items you want, the tool might guess and give too few or too many. The count can change each time, making your work inconsistent.

What not to do

Don't leave the number open or vague. If you say 'several' or 'a few,' you will get a different number each time, and your template will not line up.

Say it like this“List three main tasks from the Weekly_Plan_17May.docx.”
Not like this“List the main tasks from Weekly_Plan_17May.docx.”
C206 · What to do

Ask the model for help with tasks where repeating patterns or summarising is useful, but do not expect it to understand feelings or reasons like a colleague would.

Why

A model repeats patterns from its training or sources. The tool does not understand context, feelings, or reasons. Answers come from matching words and phrases it has seen before, not thinking or understanding like a person.

What not to do

Don't expect the model to explain why Raj chose the new supplier in his report. The model will copy phrases from the text, not explain Raj's actual thinking.

Say it like this“Summarise the main points from Sandeep_Q4Review.docx.”
Not like this“Explain why Sandeep wrote the Q4 review this way.”
C207 · What to do

Keep the source text or summary away from the model if you want a fresh answer. Only share data, facts, or an outline for the model to work with.

Why

When the model sees original text or a summary, it copies words and phrases from it. Giving only facts or an outline forces the tool to create new sentences and ideas, avoiding direct copying.

What not to do

Don't paste the project brief into the model and ask for a new version. The model will repeat lines from the brief, so the result is not original.

Say it like this“Write a project summary using these bullet points: budget, timeline, team, risks.”
Not like this“Rewrite this: Project Brief.docx.”
C208 · What to do

Tell the model to 'recall' if you want real examples it has seen, or to 'generate' if you want it to make up new examples.

Why

When the tool is told to generate, it invents details that sound real, but are made up. When told to recall, it tries to pull examples from its training or the data given, not inventing anything.

What not to do

Don't ask the model to 'generate' a client feedback example for the Q2 report if you need a real one. The model will make up a believable quote, not find an actual client comment.

Say it like this“Recall a real feedback example from Q2_Client_Comments.xlsx.”
Not like this“Generate a client comment for the Q2 report.”
C209 · What to do

Update your request if you want better answers, but remember old saved answers will not change. Only new answers use the improved request.

Why

Changing the prompt helps future replies, but any answers already created stay the same. Old mistakes or missing details remain in those saved responses, even if the new prompt is better.

What not to do

The updated prompt will not change the answers you already saved for the HR_Policy_Review.docx task. Any old answers will still appear in your results, so you may need to update them by hand.

Say it like this“Update my request for the HR_Policy_Review.docx summary.”
Not like this“Fix all old HR_Policy_Review.docx summaries.”
C210 · What to do

Use a script or spreadsheet for simple tasks like sorting, counting, or matching; let the model handle decisions or creative work.

Why

Scripts and spreadsheets run fast and cost nothing for basic actions. The model is slower and can make mistakes with exact tasks, so use it for things that need judgement, not basic chores.

What not to do

Don't ask the model to sort the list of invoice numbers in Invoice_Archive.csv. The model may miss details, and a script does it faster and more accurately.

Say it like this“Sort Invoice_Archive.csv by date in Excel.”
Not like this“Sort the invoices in Invoice_Archive.csv.”

Try these — how asking really works

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

D. What it writes when nobody is watching

Left alone, a model writes to the middle of everything it has read, and the middle is where nothing is memorable.

Fifty items come back and each one reads fine. Read together, every one opens the same way, runs the same length and lands the same beat.

Eighteen habits about sameness at volume, and why more instructions make it worse rather than better.

D211 · What to do

Ask for one entry for each different item by making the instructions clear, so every unique thing gets its own line in the list.

Why

When instructions are vague, the tool might list every time a word appears, so you end up with several identical entries. Later, you have to clean up the mess, which wastes time and causes confusion.

What not to do

Don't say 'List all the words in the document,' because the tool might repeat 'summary' three times if it shows up three times, which is not helpful.

Say it like this“List each unique project name from report_final.docx, one per line.”
Not like this“List every project name from report_final.docx.”
D212 · What to do

Remove repeated items from the list before you show the result, so each item only appears once.

Why

When repeated items stay hidden inside the list, they can sneak back in later when you use the list for something else, like sending emails or making a chart. Problems show up when you least expect them.

What not to do

Don't hide repeats only on the screen, because the duplicates are still in the list and will cause trouble if you use the list for another step.

Say it like this“Show each team member from task_list.xlsx once, even if they appear in several tasks.”
Not like this“Show all team members from task_list.xlsx.”
D213 · What to do

If two answers both seem right, rewrite the question so only one answer fits, even for someone who knows the topic well.

Why

When a question could have more than one correct answer, even experts will disagree. The question doesn't work, because the answer depends on guessing what the writer meant, not what is actually true.

What not to do

Don't leave a question as it is if two answers could be picked by a knowledgeable person, because this will always cause arguments or confusion.

Say it like this“Change the question about meeting times in calendar.csv so only one answer is correct.”
Not like this“Which times in calendar.csv are available?”
D214 · What to do

Make sure all answer choices are the same kind of thing, like all single words or all full sentences, so nobody guesses by the shape.

Why

When answer choices mix phrases with single words, people can spot the odd one out or guess without understanding the meaning. The question becomes a puzzle about form, not about the content.

What not to do

Don't mix answer types, like using 'office' and 'works from home on Fridays' in the same list, because the difference is obvious and not about knowledge.

Say it like this“List all department names from staff_list.csv as single words.”
Not like this“Which is correct? 'Finance', 'works in HR', 'Sales'”
D215 · What to do

Write wrong answer choices somebody could actually pick, so the question is a real test rather than a formality.

Why

When wrong answers are silly or impossible, nobody gets confused by them. The question doesn't help learning, because you only have to spot the joke, not know the right answer.

What not to do

Don't add obviously wrong options like 'banana' for a list of cities, because these don't challenge anyone and waste space.

Say it like this“Add 'Leeds' as a wrong city option in client_locations.csv.”
Not like this“Add 'Mars' as a city option.”
D216 · What to do

Write each question so it makes sense on its own, without needing to read anything before or after it.

Why

When a question only makes sense with the nearby text, it gets confusing if someone sees it somewhere else. The question loses meaning and cannot be reused in a new place.

What not to do

Don't write questions that rely on the previous paragraph, because they won't work when moved or reused in a different context.

Say it like this“Ask: 'Which manager approved the expenses in Q1_report.xlsx?'”
Not like this“Who did?”
D217 · What to do

Point out the exact mistake in the answer and explain why it is wrong, using clear language.

Why

When feedback only says 'good job' or 'try again', you do not know what to fix. Naming the specific mistake and explaining why it matters helps you avoid repeating the same error.

What not to do

Don't give vague feedback like 'incorrect' or 'try again', because it leaves you confused about what went wrong and how to improve.

Say it like this“Your formula in Budget2024.xlsx missed a bracket in cell D12.”
Not like this“Try again.”
D218 · What to do

Match your feedback to the exact wrong answer given, so the reply always fits what you actually did.

Why

When you get generic feedback that does not mention your specific mistake, it feels like no one checked what you did. You might repeat mistakes, thinking something else was wrong.

What not to do

Don't send the same error message for every wrong answer, because it makes you feel like your effort does not matter and you do not learn what to fix.

Say it like this“In Report_March.docx, you chose 'Q3' but the correct quarter is 'Q1'.”
Not like this“The answer above is not correct.”
D219 · What to do

If the answer is missing, do not make up a fake example or repeat a hint that does not fit the situation.

Why

When you see a hint that does not match what you did, you get confused. Repeated, unfitting hints make it harder to understand what actually needs to be changed.

What not to do

Don't reuse the same hint or invent a wrong answer when you do not know what happened, because it will mislead and frustrate you.

Say it like this“No date found in Invoice_112, so cannot check the due date.”
Not like this“Please check your date format.”
D220 · What to do

Never use the first example's data as a default answer in later examples, so each answer stays accurate.

Why

When the same example data appears in every answer, you start to ignore it. Later answers become wrong, and you lose trust in the tool.

What not to do

Don't copy the first example's answer into every later example, because it makes all the other answers incorrect and confusing.

Say it like this“For Sales_Jan.csv, use January's totals, not the numbers from December.”
Not like this“Use the same answer as above.”
D221 · What to do

Set a clear limit for how much text can go in a box, and make sure the box is never almost full when you start typing.

Why

When a text area is nearly full from the start, any new text makes it overflow. Scroll bars jump around, and you might think the tool is broken.

What not to do

Don't let the text area start with so much text that adding one word makes it scroll, because it looks broken and is annoying to use.

Say it like this“Limit the feedback box in Review_Tracker to 200 words.”
Not like this“Let people write as much as they want.”
D222 · What to do

Keep every paragraph short, so it's easy to read on a phone without scrolling through long blocks of text.

Why

Long paragraphs fill the screen with lines that are hard to track on a narrow display. You lose your place and miss the main idea.

What not to do

Don't write one long paragraph for everything, because it makes reading on a phone difficult and tiring.

Say it like this“Break up instructions in Onboarding_Guide.docx into short paragraphs.”
Not like this“Write the whole guide in one block.”
D223 · What to do

Ask the tool to explain its answers in plain English, so you can understand without needing technical knowledge.

Why

A machine prefers information packed tightly, because other machines process it that way. People need information unpacked and clear, or they feel confused and left out, especially if English is not their first language.

What not to do

Don't let the tool reply in technical jargon or dense language, because that makes you spend extra time figuring out what it means and you risk misunderstanding the answer.

Say it like this“Explain the steps for renaming 'Q1_report.xlsx' in plain English.”
Not like this“Summarise the file handling process.”
D224 · What to do

Introduce hard words by explaining them in simple terms first, before using them in your instructions or questions.

Why

When a new or complicated word appears without explanation, readers pause or stop. Giving a simple explanation first lets you follow along, even if you have never seen the word before.

What not to do

Do not use a technical word like 'concatenate' without first saying it means 'join together', or people may miss the meaning and get lost in the steps.

Say it like this“Show how to join, or concatenate, the names in 'staff_list.csv'.”
Not like this“Concatenate the names in 'staff_list.csv'.”
D225 · What to do

Leave out information the reader already knows, and focus on sharing new and useful details each time you answer.

Why

When you get information you already expect, your mind tunes out. Only new or surprising details keep your attention and help you learn something you did not know before.

What not to do

Don't repeat obvious facts, like 'click Save to save your file', when everyone already knows that part, or your answer feels empty and wastes time.

Say it like this“Explain why 'Q2_budget.xlsx' needs to be saved in .csv format for Rajesh.”
Not like this“Open the file, make changes, and click Save.”
D226 · What to do

Use examples with real names, files, or situations from everyday work to make your explanation clear and memorable.

Why

A specific situation, like 'Priya missed the 5pm deadline for 'client_notes.docx'', sticks in your mind. General rules fade fast, but real stories connect to your own experience.

What not to do

Don't use generic examples like 'a document' or 'an employee', because these feel distant and hard to picture, making it more difficult to remember the point.

Say it like this“Show how Ahmed can edit 'team_schedule.xlsx' before sharing it with Fatima.”
Not like this“Show how to edit a spreadsheet before sharing.”
D227 · What to do

Explain the reasons behind each step, not only what happens, so you understand how things work and not what to do.

Why

When you only hear what button to press, you might follow along but forget later. Explaining why something works a certain way helps you remember and apply the idea in new situations.

What not to do

Don't list instructions without reasons, like 'click here, then here', or you will not know what to do when the screen changes or something goes wrong.

Say it like this“Tell me why 'meeting_notes.docx' needs to be converted to PDF for Maria.”
Not like this“Convert 'meeting_notes.docx' to PDF.”
D228 · What to do

Leave out any part you are not sure about, instead of guessing or including wrong information in your answer.

Why

Missing information is obvious and can be fixed by asking again. Wrong information is believed, shared with others, and causes mistakes that are harder to spot and correct later.

What not to do

Don't guess at what a button does or invent a step, because someone may trust your answer and end up making an error that is hard to undo.

Say it like this“I am not sure if 'export' keeps the formatting in 'sales_data.xlsx'. Check and let me know.”
Not like this“Export 'sales_data.xlsx' and all formatting will be preserved.”

Try these — what it writes when nobody is watching

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

E. Data, shape, and knowing what is what

Most of what goes wrong with data is not the analysis. The problem is not knowing which version is real.

Two spreadsheets, one name, three days apart. The answer is correct for whichever one was handed over, and nobody checked which that was.

Twelve habits about shape, source and freshness — knowing what a thing is before asking anything of it.

E229 · What to do

Use a unique ID number or code to identify each item in your data, not the name or label.

Why

When two people in the team share the same name, the system cannot tell them apart. The wrong record gets picked, and nobody notices until something goes wrong—like sending Priya Sharma’s pay slip to the wrong Priya.

What not to do

Don't use names, email addresses, or job titles as identifiers. People can share these, change them, or misspell them, which leads the system to mix up their records.

Say it like this“Update employee_12345 in payroll_June.xlsx, not by Priya Sharma’s name.”
Not like this“Update Priya Sharma’s record in payroll.”
E230 · What to do

Check which file or system holds the official value for each piece of information before you update or use it.

Why

When the same detail, like a phone number, lives in both the HR spreadsheet and the office directory, one copy often gets out of date. People grab the wrong one, and messages go to the wrong place.

What not to do

Don't assume the first copy you find is correct. Different files may have different versions, and the one you use might be old or wrong.

Say it like this“Confirm Ravi’s mobile in hr_masterlist.xlsx before updating his contact in team_roster.csv.”
Not like this“Copy Ravi’s number from the team list.”
E231 · What to do

Decide what type of unique ID you will use for each item before you start building your data files or system.

Why

When you mix up which ID belongs to which kind of data, or change your mind after starting, records get lost or mismatched. People’s details can end up orphaned or linked to the wrong person.

What not to do

Don't start entering data without a clear ID plan. Changing IDs later breaks links between files and loses people’s information.

Say it like this“Set all project codes in tasks_2024.csv to start with ‘PRJ’ before adding any tasks.”
Not like this“Add tasks now, sort out IDs later.”
E232 · What to do

Add a prefix or tag to each ID when you import data from another file, not inside the original source file.

Why

When two files both use ‘001’ for different people, importing them together creates a clash. Tagging IDs as they arrive keeps each record unique without changing the original files.

What not to do

Don't edit the original files to add prefixes. Changing source data can break other systems that rely on it and makes mistakes hard to track.

Say it like this“Prefix all IDs from sales_Q1.csv with ‘S-’ during import to master_list.xlsx.”
Not like this“Change all IDs in sales_Q1.csv to start with ‘S-’.”
E233 · What to do

Keep large sets of data in separate files by type, but use the same unique ID to connect records across them.

Why

When all data types are merged into one huge file, the file becomes slow, hard to search, and easy to break. Keeping types apart but linked by a common ID makes updates and checks much easier.

What not to do

Don't put every detail—contacts, projects, hours, payments—into one spreadsheet. Large, mixed files are hard to manage and prone to errors.

Say it like this“Link project_2024.csv and staff_hours.csv by employee_id instead of merging everything.”
Not like this“Combine all project and hours data into one big file.”
E234 · What to do

Set up automatic checks in the tool or form that creates your data to catch missing or wrong values before saving.

Why

When data gets entered without checks, mistakes like missing dates or wrong totals slip through. Errors such as these only come to light later, after the records have spread to other files and systems.

What not to do

Don't wait until the final report to find missing or wrong fields. Early errors are much harder to fix once they spread.

Say it like this“Make the leave_form.xlsx require a date and reason before saving.”
Not like this“Review leave requests for missing details at the end of the month.”
E235 · What to do

Check every quoted phrase or sentence in your document to make sure it actually appears where the tool says it does.

Why

A single character missing from a quoted phrase can break the connection, so the reference link disappears and the feature does not work. The tool gives no warning, so nobody knows why it failed.

What not to do

Don't copy a phrase from memory or guess what was written, because a missing comma or word means the tool cannot find it and the link fails without notice.

Say it like this“Find 'Q2 targets' in the June_report.docx summary section.”
Not like this“Show the quote from the report.”
E236 · What to do

Make the tool show a clear error message when something it needs is missing, instead of hiding the problem or continuing silently.

Why

When a part is missing but the tool stays quiet, people think the feature is broken or buggy. Hours get wasted looking for a bug that is really a missing file or piece.

What not to do

Don't let the tool skip over missing files or data without any message, because people will not know what went wrong and will spend days searching for a fix.

Say it like this“Alert if the sales_data.csv file is not found in the folder.”
Not like this“Ignore missing files and run anyway.”
E237 · What to do

Save common search results once on the main server so everyone can use them, instead of making each person run the same search separately.

Why

Running the same search for every person uses up the computer’s time and power over and over. The results are the same, but the work is repeated for no reason.

What not to do

Don't let each person run the same search for 'weekly_sales.xlsx' on their own, or the server will slow down and waste energy.

Say it like this“Store the top 10 queries for the team in the shared_results folder.”
Not like this“Let everyone search the same file themselves.”
E238 · What to do

Get answers for the most common questions ready ahead of time, and only make people wait for answers to unusual questions.

Why

Most people ask the same questions, so having those answers ready saves time. Unusual questions are rare and do not slow things down much if they take longer.

What not to do

Don't treat every question as new, or people will wait for answers to things like 'latest leave policy' that could be ready instantly.

Say it like this“Preload answers for 'annual leave policy' and 'expense claim form' in advance.”
Not like this“Wait to answer every question as it comes.”
E239 · What to do

Move your data into a real database before your file, like 'contacts_list.csv', gets so large that opening it becomes slow or fails.

Why

Big files take longer and longer to load as they grow. By the time you notice, opening or searching the file is already slow or broken, which stops your work.

What not to do

Don't keep adding names to 'contacts_list.csv' forever, because once it gets huge, the file will not open or search quickly enough to use.

Say it like this“Import contacts_list.csv into the office database before it reaches 10,000 rows.”
Not like this“Keep everything in the same spreadsheet.”
E240 · What to do

Set up searches to look for the meaning of what you ask, not only exact words, so you find ideas even if the words are different.

Why

Searching for exact matches misses files that use different words for the same idea. People waste time looking for something that is there, but written another way.

What not to do

Don't search only for 'annual review' if the document uses 'yearly appraisal', or you will miss what you need and spend extra time looking.

Say it like this“Find files about 'annual review' or 'yearly appraisal' in HR_policies.docx.”
Not like this“Search only for 'annual review' keyword.”

Try these — data, shape, and knowing what is what

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

F. Judgment — what you never hand over

Judgment is the part that does not transfer, and the part worth protecting.

The recommendation is well argued and confidently wrong, and the reason it is wrong is something you know and the model could not.

Eighteen habits about what stays yours: the decision, the check that carries consequence, and the line between advising and acting.

F241 · What to do

Describe the full range of work, not only a single summary number, when sharing what the tool covers.

Why

A single number, like '500 templates', hides the variety and complexity inside. People may miss important details or think everything fits into one small box. Work done over centuries cannot be shown by a tidy label.

What not to do

Don't reduce a wide field to a count or single label. People will not see the real size, and may ignore what is missing or unique.

Say it like this“Show examples from the 500 templates, like Invoice_2023.docx and ProjectPlan_March.xlsx.”
Not like this“List all 500 templates.”
F242 · What to do

Use lists for things you can fully name, like file types. For bigger groups, like stories or tones, provide a way to create new ones.

Why

Closed sets can be listed because all items are known. Open sets, such as creative ideas or writing styles, keep growing. A list alone cannot cover every possibility, so people need a way to add or make new options.

What not to do

Don't try to make one giant list for ideas or styles. People will think the list is complete and miss out on new or custom choices.

Say it like this“Let me add a new tone for my email to Priya about the April report.”
Not like this“Show every possible tone.”
F243 · What to do

Check if a template or file already exists before asking the tool to create a new one.

Why

Duplicate work happens when people do not look for existing resources. Time and effort are wasted making what is already there, like buying more apples when the basket is already full.

What not to do

Don't ask the tool to make something from scratch without searching first. You may end up with two copies or miss a better version.

Say it like this“Find out if a 2023 invoice template already exists before making one.”
Not like this“Create a new invoice template.”
F244 · What to do

Estimate time for tasks based on how fast the tool works, not how long people usually take.

Why

People often guess time using their own pace, but the tool may finish much faster. Wrong estimates can ruin schedules, like planning a race with the wrong distance.

What not to do

Don't plan using human speed for tasks the tool can do in seconds. You risk missing deadlines or wasting time.

Say it like this“Check how long it takes to summarise Budget2024.xlsx using the tool.”
Not like this“Assume it will take 30 minutes to summarise the file.”
F245 · What to do

Describe what the tool will include or change in a task, not only how long it will take.

Why

Time alone does not explain what is being done. If you only hear 'a month', you cannot tell what is new or reused. Plans become guesses, like picking a box without knowing what is inside.

What not to do

Don't say only how long something will take. People need to know what is included so they can plan or check the results.

Say it like this“List what will change in the April_Sales.pptx update, not only the time needed.”
Not like this“The update will take two weeks to finish.”
F246 · What to do

Fix the real problem in a process or file, not only cover it up with retries or warnings.

Why

Temporary fixes, like retries or warnings, hide faults instead of solving them. Problems may grow unseen, like a pipe leaking behind tape, until they cause bigger trouble later.

What not to do

Don't rely on retries or error messages to handle faults. The real issue stays hidden and may get worse.

Say it like this“Find out why Budget2023.xlsx keeps failing to upload, and fix the cause.”
Not like this“Retry uploading the file if there is an error.”
F247 · What to do

Stop and rethink your idea if two different prompts fail to make the right picture for the same project, such as the 'Q3 Invoice Cover' for Rajesh.

Why

Repeating the same idea with small changes usually leads to the same wrong result. The shapes and plan are the problem, not the specific wording. A new approach with a different image often works quickly.

What not to do

Tweaking the same prompt over and over for the 'Q3 Invoice Cover' wastes time and energy when the idea itself is what is not working.

Say it like this“Try a new concept for 'Q3 Invoice Cover' after two failed attempts.”
Not like this“Change the colour and try again for 'Q3 Invoice Cover'.”
F248 · What to do

Switch your approach if your first picture looks like something you did not want, such as a 'cake' when you needed a 'pie' for 'Finance Report Chart'.

Why

The first shapes chosen guide the picture’s meaning. If the result is off, changing small details or softening features will not make it say the right thing. Starting again with a new plan works better.

What not to do

Editing a picture that looks wrong for 'Finance Report Chart' only makes a bad fit look slightly different, not correct.

Say it like this“Start over with a new prompt for 'Finance Report Chart'—need a pie, not a cake.”
Not like this“Make the cake picture rounder for 'Finance Report Chart'.”
F249 · What to do

Check real, successful examples before making more pictures, especially if the first two tries for 'Team Roster Slide' did not work.

Why

Planning based only on file names or titles misses what actually works. Looking at finished, good examples shows what details and style succeed, so your next attempt is based on proof, not guesswork.

What not to do

Making a third 'Team Roster Slide' based on your memory of the name repeats the mistake of not learning from what has actually worked.

Say it like this“Review last quarter's 'Team Roster Slide' files before making a new one.”
Not like this“Try another version for 'Team Roster Slide' from the same prompt.”
F250 · What to do

Use a picture or symbol from your own checked folder for 'HR Policy Update' before searching for a new one online.

Why

A matching symbol in your own collection is already checked for style and meaning. Skipping it for a general one wastes time and risks using something that does not fit your team's way of working.

What not to do

Grabbing a random symbol from the web for 'HR Policy Update' when you have a matching one saved ignores your own quality-checked collection.

Say it like this“Use the approved 'HR_Policy_Icon.png' from the shared folder for this update.”
Not like this“Search Google for a new icon for 'HR Policy Update'.”
F251 · What to do

Figure out why the first batch of 'Product Launch Posters' failed before resizing or making changes for the next try.

Why

Guessing at the problem and trying again without understanding wastes budget and damages trust. The same mistake is likely to happen if you do not know what went wrong the first time.

What not to do

Resizing and re-sending 'Product Launch Posters' right after a failed batch repeats the error and wastes resources.

Say it like this“Check feedback on 'Product Launch Posters' before making new sizes.”
Not like this“Resize and send 'Product Launch Posters' again.”
F252 · What to do

Pick the right AI model for your task, such as 'Presentation Slides', and try the lowest-cost capable one first.

Why

Some jobs need more capable models, but not always the biggest or most expensive. On one task, a well-chosen model was much cheaper and faster than the smaller ones, with no drop in quality.

What not to do

Starting with the smallest or most expensive model for 'Presentation Slides' every time can waste time or money if another model is a better fit.

Say it like this“Run 'Presentation Slides' with the mid-tier model to check speed and cost.”
Not like this“Use the default model for every 'Presentation Slides' job.”
F253 · What to do

Check early whether the AI tool can handle the type of task you want, like reading a scanned invoice or analysing a chart.

Why

Many AI models have hard limits, such as not being able to read handwriting or extract information from complex diagrams. You notice these gaps before you rely on the tool, avoiding wasted effort.

What not to do

Don't assume the system can handle every file, or you might build a process that fails at the first step.

Say it like this“Can you read the table in 'Q2_Expense_Report.pdf' and list the totals?”
Not like this“Process all our scanned invoices for July.”
F254 · What to do

Before starting a large job, confirm agreement on the task, test a small sample, get approval, and check the cost with your manager or team.

Why

Skipping one of these steps often means doing a lot of work that nobody wants, or that costs too much, or that fails basic checks. Early checks save time and budget.

What not to do

Don't run a full batch before showing a test or checking the price, or you risk wasted budget and time.

Say it like this“Let's test five rows from 'ClientList_May.xlsx' and get approval before the full batch.”
Not like this“Go ahead and process all 2,000 contacts.”
F255 · What to do

Treat the checking tool as a way to review results, not as the final work you deliver to your colleague or manager.

Why

Spending time making the review tool look perfect blurs the line between draft and finished work. Colleagues may confuse a preview for the final product, leading to mistakes.

What not to do

Don't polish the review screen as if it is the final report, or people will use the wrong output.

Say it like this“Check the summary in 'Draft_Review_v1.docx', then use the final export for your report.”
Not like this“Print the review page and send it to finance.”
F256 · What to do

Reuse old prompts or templates only if they fit exactly what your colleague needs to do today.

Why

Copying a pattern because it is available or easy leads to results that might work, but do not help with the real task. The output ends up generic and not useful.

What not to do

Don't grab a template from last month for a new project unless the work matches, or your results will be off-topic.

Say it like this“Use the 'OnboardingChecklist_June.docx' template only for HR onboarding, not for IT setup.”
Not like this“Paste in the last checklist template for every new task.”
F257 · What to do

Keep the technical method hidden behind the scenes; show only clear controls for the result your colleague wants.

Why

Labels or buttons that reveal the technical method confuse people who are not interested in how it works. Controls should focus on what the person wants to achieve, not how the tool does it.

What not to do

Don't label buttons with code names or method types, or people will get lost in details they do not need.

Say it like this“Label the button 'Summarise Email', not 'Run NLP Process'.”
Not like this“Show 'Apply v2.1 Extraction Model' on the main menu.”
F258 · What to do

Show your colleague what each control or message is for, not hidden codes, step numbers, or internal labels.

Why

Stage numbers or internal codes make the tool feel unfinished and unprofessional when people see them. Removing these is easy and helps make the tool clearer and more trustworthy.

What not to do

Don't display 'Step 3: 04B_Tokenise' or similar codes, or your colleague will be confused and think the tool is not ready.

Say it like this“Show 'Review summary before sending to Rajesh' instead of a step number.”
Not like this“Display 'Stage 2.4: 003_Finish' on screen.”

Try these — judgment — what you never hand over

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

G. Making any of this stick

Everything above is worth nothing if it lives in your memory and nowhere else.

You learn something on a Tuesday, apply it beautifully, and meet the same problem in six weeks having forgotten which of the four things you tried was the one that worked.

Twelve habits about where a rule has to live to be honoured, and why anything that must never be violated cannot survive in prose.

G259 · What to do

Watch the training video, then set up a rule in your tool that checks for the mistake every time, like a checklist before sending a report.

Why

A saved video or note does nothing unless you act on it. Without a rule that runs every time, old habits return. People remember lessons when something makes them change what they do, not when they only read or watch.

What not to do

Don't save a note or video and expect your behaviour to change. A lesson sitting in a folder will not remind you in the point you need it.

Say it like this“Add a daily check for 'Q2_Report.xlsx' before sending to Priya.”
Not like this“Watched the video, so I won’t miss mistakes now.”
G260 · What to do

Write down what happened in your archive, then set a separate rule in your tool that runs every time you do that task again.

Why

Stories and records help you learn, but unless you put a rule in place that acts each time, you will repeat the same error. Memory fades, but a rule brings the lesson back exactly when needed.

What not to do

Don't put the story and the rule in the same place and expect you’ll remember. Writing both together means the rule gets buried and isn’t used when you need it.

Say it like this“Archive the error in 'April_Incident_Log.docx', then set a new check for totals in invoices.”
Not like this“Wrote the story, so I’ll remember next time.”
G261 · What to do

Practise using your rules in real situations, not only reciting them. Set up reminders or blockers so you use them under pressure.

Why

People can repeat all the rules perfectly, but when deadlines hit, stress makes them forget. Only rules that actually run in the point help you stick to them, especially when you’re busy or distracted.

What not to do

Don't assume knowing the rules means you’ll follow them. Under stress, you can break several rules without even noticing if nothing reminds you.

Say it like this“Set a pop-up in 'Monthly_Budget.xlsm' to check before sending to Anil.”
Not like this“I know all the rules, so I’ll follow them.”
G262 · What to do

Choose a tool or setting that blocks mistakes automatically, like a file lock or a required field, so you cannot skip the safety step.

Why

When a tool blocks the mistake, you don’t have to remember to be careful. If the safety step is optional, it gets skipped when you’re in a rush, so errors slip through at the worst times.

What not to do

Don't rely on your memory to catch every error. Optional checks get skipped, especially when you’re late or distracted.

Say it like this“Set a password on 'Payroll_June2024.xlsx' so no edits happen by accident.”
Not like this“I’ll remember not to change the payroll file.”
G263 · What to do

Set up a separate checker—like a second person or an automated rule—so the person doing the work cannot approve their own changes.

Why

A blocker that is not the person doing the task catches mistakes every time. When the checker and the actor are the same, errors slip through because people get used to their own habits.

What not to do

Don't let the same person check their own work. Familiarity makes it easy to miss mistakes that a separate checker would catch.

Say it like this“Ask Raj to review 'Client_Presentation.pptx' before sending to the client.”
Not like this“Checked my own slides, so they’re fine.”
G264 · What to do

List clearly which rules your tool cannot enforce, so you know where you have to pay extra attention and use self-control.

Why

No tool can force every step, like making a model explain every choice. When you know which parts need your attention, you can watch yourself and not expect the tool to do it all.

What not to do

Don't assume your tool covers every rule. Some things need your discipline, so forgetting which ones can leave big gaps.

Say it like this“Mark in 'AI_Checklist.docx' that step 4 needs manual review.”
Not like this“Tool handles everything, so I don’t need to check.”
G265 · What to do

Write each rule in full sentences that anyone could follow, with all steps spelled out and no abbreviations or inside jokes.

Why

New people feel lost when rules use short forms or private language. When you write everything clearly, anyone who joins later can understand what to do without guessing or asking for help.

What not to do

Don't write rules like 'No shortcuts in docs' or use initials and codes. New joiners will miss what matters, and mistakes get repeated.

Say it like this“Write out every step for 'AI-Invoice-Checks.txt' with no abbreviations.”
Not like this“Nvr use shrtcts in AI docs.”
G266 · What to do

Choose full explanations for each rule, using plain words and examples, so someone in a hurry can follow along when something breaks.

Why

People only read these files when something has gone wrong. Dense notes or technical shorthand make them waste time guessing what to do, instead of fixing the problem.

What not to do

Don't fill the notes with one-liners or technical codes. When someone needs help, they will not know what to do next.

Say it like this“Explain the backup steps for 'Client-Data-Restore.txt' in clear sentences.”
Not like this“Restore: cd > rstr > run”
G267 · What to do

Keep the main file with rules short and focused, so the most important instructions are easy to spot without scrolling through pages.

Why

People skim long lists and miss what matters most. When you keep the file tight, the rules that prevent mistakes stay visible, even on a busy day.

What not to do

Don't add every possible tip or warning to the main file. People will ignore the whole thing if it looks too long.

Say it like this“Keep 'AI-Process-Rules.txt' to one page, with only the steps that everyone uses.”
Not like this“Add every AI note you hear to the main rules file.”
G268 · What to do

Add each new note or rule to the log without deleting older entries, so the full history of changes stays in the file.

Why

When you erase old notes, nobody can see why a rule changed or what went wrong before. Keeping the full story helps everyone understand past decisions and avoid old mistakes.

What not to do

Don't overwrite or remove previous log entries. The team loses the reasons behind changes, and repeats past errors.

Say it like this“Append the June update to 'Meeting-Log-2024.txt', leaving all earlier notes in place.”
Not like this“Delete last month's notes before adding the June update.”
G269 · What to do

Update the shared record with all details of your work before you tell anyone the task is finished, so nothing is forgotten.

Why

When you wait until later, you forget the small but important details that explain what you did. Next time someone checks, the steps are missing and problems repeat.

What not to do

Don't mark a job as done and promise to update the record later. People will miss the details that matter most.

Say it like this“Fill in 'AI-Checks-Log.txt' with what changed before emailing Priya that the job is done.”
Not like this“Tell Priya it's done, then update the log tomorrow.”
G270 · What to do

Only keep rules in the main file that came from actual mistakes, so every instruction solves a real problem someone faced.

Why

When you add guesses or warnings that never happened, the file fills with clutter. People stop trusting or following the rules, and real lessons get buried.

What not to do

Don't add imagined problems or warnings that have not happened. The file becomes too long, and nobody can tell what matters.

Say it like this“Add a rule to 'AI-Process-Rules.txt' because Sarah missed a step last week.”
Not like this“Write a rule for every possible error, even if no one has made it.”

Try these — making any of this stick

No score, and nothing to finish. Every wrong answer opens with why the wrong idea was tempting.

Question 1 of 12
 

The questions people still ask

Why does my AI tool keep mixing up file names like Report_Q1.docx and Report_Q2.docx in my lists?
Naming mix-up

AI tools can jumble similar file names, especially when lists are long or names look alike. Double-check that each file is mentioned separately in your prompt. Point out differences, such as dates or versions, so the tool keeps them apart.

What should I do when my AI tool gives me answers that look too generic for my project with Priya and Mark?
Too generic
  • Add specific names, like Priya or Mark, in your question.
  • Describe the project or task in detail.
  • Avoid phrases like 'best practices' or 'tips'.
  • Ask for examples from your real files or meetings.
  • Mention deadlines or tools you use, such as Excel or Slack.
How do I get my AI tool to use the right columns from my sales_data.csv file when making a chart for Monday's meeting?
Data mismatch
  1. Tell the tool the exact column names you need, like 'Region' and 'Total Sales'.
  2. Say what kind of chart you want, such as a bar or line chart.
  3. Check the tool's preview to make sure it matches your request.
  4. Save or export the chart, then open it to confirm the data is correct.
Why does my AI tool sometimes leave out my extra notes at the bottom when I ask for a summary of my weekly report?
Missing content

AI tools often focus on the main sections at the top or middle of a document. Mention that your summary should include notes from the end as well. Point to the section by its heading or page number if you can.

How can I check if my AI tool is showing my spreadsheet data in the right format before I send it to my manager?
Format error
  1. Review the output for missing columns or rows.
  2. Look for number formatting, such as currencies or percentages.
  3. Check that dates appear in the correct order and style.
  4. Compare a few entries to your original spreadsheet.
Why does my AI tool sometimes change the layout when I switch from my laptop to my phone?
Layout shift

Screen size changes can cause layouts to shift. Check your design on both devices before sharing. Leave space for things like the chat bar or notifications, so nothing important gets covered or lost.

What can I do if my AI tool keeps repeating the same suggestion for different tasks in my project with Fatima?
Repeat answers
  • Make each task prompt specific to Fatima's role or deadline.
  • Describe the task in detail, not only by project name.
  • Ask for unique suggestions for each step.
  • Mention what has already been tried or decided.
How do I stop my AI tool from making up information about my client meeting with Rahul on Friday?
Invented info
  1. Ask the tool to use only details from your meeting notes.
  2. Tell it not to add anything you have not written down.
  3. Check the summary for any new or strange details.
  4. Edit or remove anything that does not match your real notes.
Why does my AI tool sometimes pick strange colours or fonts when designing a slide for my quarterly review?
Style mismatch

AI tools use default styles unless you tell them what to use. Give the tool your brand colours and font names, or choose from the options in your design system. Check the finished slide before you present.

What is the difference between asking my AI tool for a summary and asking for action points from my project update?
Output type
RequestWhat you get
SummaryA short version of the whole update, covering all main ideas.
Action pointsA list of tasks or next steps, usually with names and deadlines.
How do I tell if my AI tool is using the correct date format from my HR_attendance.xlsx file?
Data format
  1. Open your HR_attendance.xlsx file and check the date column format—day-month-year or month-day-year.
  2. Ask the AI tool to show a sample of dates it reads from the file.
  3. Compare the sample with your original file to confirm the order matches.
  4. If the order is wrong, tell the AI tool the exact format you need and ask it to re-read the data.
Why does my AI tool sometimes skip over my comments in the feedback section of my project_plan.docx file?
Hidden content

Many AI tools focus on the main content and may not read comments or footnotes unless you ask directly. If your feedback is in a comment, mention the comments section in your question so the tool includes it. Comments can be hidden by default, so always specify if you want them.

How can I get my AI tool to use the same numbering style as my team’s meeting notes from last week?
Format matching
  1. Find an example of the numbering style in your team’s meeting notes.
  2. Copy a short section with the correct numbers and paste it into your AI tool prompt.
  3. Ask the AI tool to match the numbering style exactly, using your pasted sample.
  4. Check the output for the same style before sharing with your team.
What should I do if my AI tool mixes up the order of agenda items when drafting an email for my team?
Order error
  • List each agenda item on a separate line in your prompt.
  • Tell the tool to keep the order exactly as given.
  • Review the draft and check the order before sending.
  • If an item moves, point out the mistake and ask for a correction.
Why does my AI tool sometimes not recognise the difference between a contact number and an invoice number in my client_list.csv?
Column confusion

Similar column names or number formats can confuse the AI tool. Make sure you use clear column headers like 'Contact_Number' and 'Invoice_Number'. When asking for details, mention the exact column name so the tool picks the right one every time.

How do I make my AI tool keep the table layout from my budget_2024.xlsx file when creating a summary for my manager?
Layout copy
  1. Show the AI tool a screenshot or example of the table layout you want.
  2. Tell the tool to use the same row and column structure in the summary.
  3. Ask for a preview before sending it on.
  4. Check the summary matches your original layout before sharing.
What can I do if my AI tool adds extra spaces or line breaks when writing a message for my Slack group?
Formatting error
  • Paste the message into Slack’s draft window first to spot extra spaces.
  • Tell the AI tool to use single spaces and standard line breaks.
  • Remove any double spaces or blank lines before posting.
  • If the problem repeats, mention the exact spacing you want in your next prompt.
Why does my AI tool sometimes give different answers when I ask the same question twice about my sales targets?
Inconsistent output

AI tools can change answers based on small differences in your question or the context from earlier messages. To get consistent results, use the same wording each time and start a new chat if you want a fresh answer with no history.

How do I compare what my AI tool writes for a summary versus a detailed report for my monthly marketing update?
Output comparison
FeatureSummaryDetailed Report
LengthShort, 3-5 sentencesLong, several paragraphs
DetailKey points onlyAll main points, examples, and data
UseQuick updateFull review or record
AudienceBusy colleaguesManagers or clients needing full context
What should I check if my AI tool writes a design that looks too crowded on my phone screen?
Mobile layout
  • Open the design on your phone and scroll through every section.
  • Check if buttons or text overlap or run off the edge.
  • Look for small tap areas that are hard to press.
  • Ask the AI tool to add space between elements if anything feels tight.
How do I check if my AI tool is using the right version of my document when working on my Q3_report.docx?
File version

Check the file name and last modified date shown in the tool before starting. Compare this with the version saved on your computer or cloud drive. If the tool shows an older date or a different file name, upload or select the correct version before continuing.

Why does my AI tool sometimes miss out on the difference between a task for Rina and one for Deepak in my project_todo.xlsx?
Data mix-up

AI tools often group similar names or roles together if instructions are not clear. Always mention both the name and the specific task next to each entry. Double-check the list after processing to see if each person’s task is shown separately.

What should I do if my AI tool keeps splitting my address from address_line1 and address_line2 into separate paragraphs in my client form?
Formatting trouble

Keep both address lines in the same cell or field before sending them to the tool. Add a single comma or line break between them. Tell the tool to combine both lines as one address, so they stay together in the output.

How do I ask my AI tool to write a summary of my meeting notes for my manager without missing action items?
Summary detail
  1. Start by asking for a summary of the meeting notes.
  2. Add a request to list all action items separately at the end.
  3. Check the output for missing or vague actions.
  4. If any actions are missing, ask the tool to review the notes again, focusing only on tasks.
Why does my AI tool sometimes choose the wrong logo file when I ask for a design for my client pitch deck?
File selection

AI tools may pick the first logo file they find if several are available. Name each logo file with the client’s full name—like 'Asha_Consulting_logo.svg'—and mention the exact file name in your request. Double-check the design output before sharing.

How do I make sure my AI tool keeps the bullet points in my weekly update email to Priya clear and not merged together?
Clear lists
  1. Write each point as a separate line in your draft.
  2. Tell the tool to keep each point as a separate bullet.
  3. Review the output to spot any merged or combined points.
  4. If points are merged, ask the tool to split each idea onto its own line.
What can I do if my AI tool keeps changing the order of my slides when exporting my training_deck.pptx for mobile viewing?
Slide order

Export the slides in the original order from your desktop. When using the tool for mobile, check the slide order before sharing. If slides are out of order, re-upload the file and ask the tool to keep the order exactly as in 'training_deck.pptx'.

Why does my AI tool sometimes put too much text on one screen when I view my project summary on my phone?
Screen fit

AI tools often do not know the screen size unless told. Ask for shorter paragraphs or use bullet points. Before sending, check the summary on your phone and ask the tool to shorten sections that look crowded.

How do I compare how my AI tool writes a summary for my monthly sales report versus a summary for my weekly team meeting?
Summary comparison
TypeMonthly Sales ReportWeekly Team Meeting
FocusNumbers, trends, targetsTasks, updates, next steps
LengthLonger, with detailsShorter, quick points
AudienceManagers, finance teamTeam members
LanguageFormal, specificCasual, direct
What should I do if my AI tool leaves out the attachments when drafting an email for my client, Anjali, about the new contract?
Attachment mention
  • Mention each attachment by file name in your draft.
  • Tell the tool to reference the files in the email body.
  • Double-check the final draft for missing attachment mentions.
  • Add a reminder line if any file is not listed.

What the rules give back

A hundred and thirty-seven habits, and the last one is the only one that matters on its own: anything that must never be violated cannot live in prose. Write it where it is enforced, or accept that it will hold until the day it does not.

Copyright © Pawan Nayar · LLOS.ai · 2026 — Original pedagogy, voice, and design — all rights reserved.