Doctors need simple, clean ways to share their professional identity. Patients need easy access to reliable contact details. And most existing “digital business card” tools are either bloated, generic, or too rigid.

So I decided to build my own.

Starting Point: Almost No Coding Background

I have minimal coding experience. Enough to understand structure, not enough to build a full platform from scratch.

In the past, this would have stopped me.

This time, I used Claude Code.

That changed everything.

The Shift: From Coding to “Vibe Coding”

Instead of thinking like a traditional developer, I approached it differently. I described what I wanted. I iterated quickly. I tested constantly. I refined based on feel and usability.

This is what I call “vibe coding.”

You are not writing every line manually. You are guiding the system. You are the product owner, QA tester, and designer at the same time.

The AI becomes your developer.

What I Built

I ended up building a multi-user virtual business card platform with two key products:

1. vCard for Doctors

• Clean, professional layout
• Focus on clinical identity
• Easy sharing with patients
• Mobile-first design

2. vBizCard for Everyone

• More flexible and customizable
• Suitable for entrepreneurs, freelancers, and general users
• Personal branding focused

This was not just a static page generator. It supports multiple users, each with their own card, hosted and managed centrally.

That is a real product, not a prototype.

What Surprised Me

1. Speed of iteration

I could go from idea to working feature in hours, not weeks.

2. Lower barrier than expected

You do not need deep technical knowledge. You need clarity of thought.

3. The importance of prompting

Bad instructions produce messy results. Clear instructions produce clean systems.

This is the real skill.

4. Debugging is still real

AI helps, but things still break. You need to think logically, test assumptions, and not blindly trust outputs.

What Was Hard

This was not magic.

• Understanding file structure and deployment still matters
• Fixing edge cases takes time
• UI consistency needs manual attention
• Hosting, domains, and redirects can be more painful than coding

AI reduces effort, but it does not remove responsibility.

Key Insight

The bottleneck is no longer coding skill.

The bottleneck is:

• clarity
• decision making
• persistence

If you know what you want, you can build far more than before.

If you don’t, AI will just amplify confusion.

Why This Matters

This changes how products are built.

You no longer need:

• a full dev team
• long timelines
• large budgets

A single person with domain knowledge can now build usable tools.

For me, this means:

• building tools for doctors directly
• iterating based on real clinical needs
• bypassing slow, generic solutions

What’s Next

This is just the first version.

Next steps:

• better templates and design presets
• analytics for card usage
• deeper integrations (appointments, messaging)
• scaling the multi-user system

The goal is simple. Make it effortless for anyone to create and share a professional identity.

Final Thought

This was not about learning to code.

It was about learning how to think clearly, communicate precisely, and iterate quickly.

That is the real skill now.

And once you get it, the ceiling disappears.

I wanted my phone to simply tell me my schedule, clearly and automatically. Not just the event titles, but the start times as well.

So I decided to build a Shortcut on my iPhone that would read out my appointments each morning.

The problem? Apple Shortcuts is powerful, but not always intuitive.

That is where ChatGPT helped.

The Objective

Create a Shortcut that would:

Pull all calendar events for the day Exclude irrelevant entries Speak each appointment Include the start time Sound natural when read aloud

In short, I wanted something that behaved like a quiet personal assistant.

Where I Got Stuck

Initially, I made a common mistake.

I used “Get Text from Calendar Events.”

It looked logical. But it flattened the data into messy text. Once that happens, you lose access to structured fields like:

Event title Start time Location

ChatGPT immediately pointed out the flaw.

Do not convert structured data into text too early.

Instead, iterate through the events properly.

This single correction saved me a lot of frustration.

The Architecture ChatGPT Recommended

The logic was surprisingly elegant:

Find Calendar Events ? If any exist ? Repeat through each event ? Format the time ? Build a sentence ? Speak it

What mattered most was using the Repeat with Each action. That is what exposes the event properties inside Shortcuts.

Once inside the repeat block, I could access:

Repeat Item ? Title Repeat Item ? Start Date

Then format the time into something human:

“9:00 AM — Clinic”

Clean. Audible. Useful.

Another Subtle Lesson

At one point, I could not find “Repeat Item ? Title.”

Turns out the issue was structural.

My Text action was slightly outside the Repeat block. Shortcuts hides the event fields unless the hierarchy is correct.

This is exactly the kind of small, high-friction detail that wastes time when you are figuring things out alone.

ChatGPT diagnosed it instantly.

Move the Text action inside Repeat. Problem solved.

The Upgrade I Did Not Know I Needed

Originally, the phone would speak each event separately.

Functional, but robotic.

ChatGPT suggested combining them into one flowing agenda:

“Your appointments today are: 9 AM ward round. 11:30 AM clinic. 3 PM transplant meeting.”

Much more natural.

Small design choices matter when you interact with a system daily.

Why This Matters More Than It Seems

This was not about saving a few seconds.

It was about reducing cognitive load early in the day.

When your schedule is read aloud:

You don’t scan. You don’t interpret. You just absorb.

Decision bandwidth is preserved for things that actually require judgement.

Clinicians, founders, and operators all benefit from this.

What This Experience Reinforced for Me

1. ChatGPT is excellent at procedural intelligence

Not just answering questions, but guiding step-by-step construction.

2. It shortens the experimentation loop

Instead of trial-and-error for 45 minutes, you converge in minutes.

3. It helps you think like a systems designer

The biggest gain was not the Shortcut itself. It was understanding how to structure automations properly.

Once you see the pattern, you start spotting dozens of opportunities.

Where This Goes Next

Now that the foundation works, the obvious extensions are:

A full morning briefing Calendar + reminders + key emails Travel buffer warnings Detect back-to-back meetings Priority tagging Only read high-value events AI summarisation of the day ahead

We are moving toward a world where your phone behaves less like a tool and more like an operational partner.

Quietly. Reliably. In the background.

Final Thought

Many people still think of ChatGPT as something you ask questions.

That is the shallow use case.

The real leverage comes when you use it to build small systems that improve how your day runs.

This Shortcut took minutes to assemble once guided properly.

Yet it removes friction every single morning.

That is a high return on a very small investment.

In these stories, people pasted symptoms, lab results, or scan reports into a chatbot. The AI highlighted red flags and urged urgent care. Clinicians later confirmed serious disease. The value was speed, pattern recognition, and persistence. Not certainty.

This does not make AI a doctor. It makes it a gap-filler. Short consults, fragmented records, delayed follow-up. These are real failures. A language model that reads everything and responds instantly can change the timeline. In emergencies, that matters.

Doctors should be skeptical but not dismissive. Yes, AI can hallucinate. Yes, it lacks examination and accountability. But it also listens without interruption and never gets tired. Ignoring that advantage is risky.

The bigger risk is not patients using AI. The bigger risk is pretending they are not. Patients will use these tools anyway. The smart move is to guide them. Position AI as triage and augmentation, not diagnosis. Build pathways for rapid human review when AI raises alarms.

When a patient says “a chatbot saved my life,” the real message is this. The system was too slow, and something else stepped in.