I Built a Tip & Bill-Split Calculator with AI (No Coding Needed)

 We have all been there. The bill arrives, five friends stare at it, someone reaches for a phone calculator, and someone else says "just split it evenly." Then the tip math begins and the table goes quiet.

I decided to fix that with AI. I asked Claude to build me a tip and bill-split calculator, and about a minute later I had a working app. No coding, no installing anything, no app store. You can try it right now on my site: eliteneoai.netlify.app

In this post I will show you the exact prompt, what the app does, and how you can build and customize your own.

What the calculator does

The app is simple on purpose:

• Enter the bill amount
• Tap a quick tip button (10%, 15% or 20%) or type your own custom tip
• Set the number of people with big + and − buttons
• Instantly see the tip, the total, and what each person pays

It also has a dark mode toggle, large tap-friendly buttons, and a layout that works well on a phone, which is where you will use it most.

The prompt I used

This is the exact prompt I gave Claude:

Make a tip and bill-split calculator in one HTML file. Inputs for bill amount, tip % (with 10%, 15%, 20% quick buttons) and number of people. Show tip, total, and amount per person. Clean modern design, large buttons, dark mode toggle, works on mobile. Keep the code beginner-friendly.

A few things made this prompt work well:

1. Clear inputs and outputs. I listed what goes in and what comes out, so nothing was left to guess.
2. Specific design requests. "Large buttons," "dark mode" and "works on mobile" told the AI exactly how it should look and behave.
3. "One HTML file." This keeps everything simple. No folders, no frameworks, no setup.
4. "Beginner-friendly." This is my favorite line. It makes the AI add comments and write readable code, so you can learn from it.

How the code is organized

Even if you have never written code, the file is easy to follow because it has three parts:

• CSS (the look): colors, spacing, button sizes and dark mode. All the colors live in one block at the top, so changing the theme means editing a few values.
• HTML (the structure): the input boxes, the tip buttons and the results area.
• JavaScript (the brain): one small calculate() function that reads your numbers, works out the tip and total, divides by the number of people, and updates the screen.

The math is only a few lines:

const tip = bill * tipPercent / 100;
const total = bill + tip;
const each = total / people;

That is the heart of the whole app. Everything else is making it look good and feel nice to tap.

How it looked

Light Theme

Dark Theme

How to deploy it yourself

I deployed mine on Netlify, which is free for small projects like this:

1. Save the HTML file to your computer (for example as index.html).
2. Go to Netlify and drag and drop the file or folder onto their deploy page.
3. Netlify gives you a live link you can share with anyone.

That is it. No server and no coding setup. My copy is live on EliteNeoAI.netlify.app.

Ideas to make it your own

Once you have the basic version, you can ask the AI to add more. A few ideas:

• A round up button so each person pays a whole number
• A currency selector (₹, $, €)
• Different tip presets for different countries
• A custom color theme to match your brand
• An option to split unevenly when someone ordered less

To add any of these, paste your current code back into the AI and describe the change in plain English.

Why this matters

This little calculator is a good example of what AI tools can do today. You do not need to be a developer to build something useful. You need a clear idea and a clear prompt. Small tools like this are also a great way to learn how code works, because you can read, tweak and break things safely.

If you build your own version, I would love to see it. Tell me in the comments what app you want me to build next. I am also making a video about this on my YouTube channel, EliteNeoAI, so keep an eye out for it.

Happy building!

When AI Draws Me a Dog I Never Had (And What It Means)

I tried a trending prompt: 

  "Create a caricature of me based on what you know from our chats."

Most of it was spot on: my work, my interests, my creator life. Then I noticed a dog in the corner, labeled as my stress buster.

I don't own a dog, and I've never talked to the AI about one. When I asked where it came from, the answer was basically: it seemed like a fitting detail.

What happened

The AI didn't look up a hidden fact about me. It filled a gap with a plausible invention.

Caricatures have a pattern. They usually include a work setup, a signature trait, and a hobby or stress relief. The AI had my work and interests but nothing for the last slot, so it made one up.

It predicts what's likely, not what's true. Image models and chatbots generate the most statistically plausible completion. For "stress buster", a dog is one of the most common answers in the data they learned from.

Confidence isn't accuracy. The dog was drawn with the same polish as the correct details, so nothing signaled that it was a guess.

Chat history is a thin sketch. AI only has fragments of what you've said. Where the fragments run out, it improvises.

This is the same behavior behind text "hallucinations", just in visual form.

Why it matters

Fun trends like this feel personal, so it's easy to treat the output as insight. But a made-up detail looks the same as a real one. If I'd posted it without checking, people would have assumed I own a dog.

The same thing happens in more serious work: invented statistics, fake citations, or tool features that don't exist.

How to get more accurate results

Set boundaries.  Add: "Only use details I've actually told you. Leave anything else out."

Ask for a source for each element. "List every item in the image and what it's based on."

Question surprises. If something looks off, ask where it came from, as I did.

Fill the gaps yourself. Give the AI your real stress buster (mine isn't a dog!) so it has no reason to guess.

Treat the output as a creative draft. It's entertainment and inspiration, not a fact sheet about you.

Final thoughts

The dog was harmless and kind of funny, but it showed me how AI works: it doesn't say "I don't know." It completes the picture. Our job is to notice what it invented and decide what to keep.

Have you caught an AI inventing something about you? Tell me in the comments.

Microsoft Teams: @Mention or Add Members to a Channel Not Working? Here's a Quick Fix

Ever tried to @mention someone in a Teams channel and found they don't show up in the list? Or maybe you tried to add a member to a channel and nothing happened. It's a frustrating one, but there's a simple workaround.

What's going on?

Teams sometimes fails to sync the channel's membership data properly. The fix is to force a membership refresh by making at least one membership change.

The workaround

Make one membership change, using either of these methods:

1. Add a new member or remove an existing one.
2. Switch an owner to a member, then switch them back to an owner.

Where to make the change

The right level depends on the type of channel:

• Shared channel: make the change at the team level.
• Private channel: make the change at the channel level.

Final thoughts

Once the membership change is saved, Teams should refresh the member list, and @mentions and adding members should work again. If this helped, share it with a colleague who is stuck on the same problem. If the issue continues, let me know in the comments.