Vibe Coding Reality Check

I was really excited about this hackathon because it was an offline event and completely focused on prompting and building a web game using AI.

But very quickly, I realized this experience was going to teach me much more than I expected.

The prototype had to be built only using AI Studio or Antigravity, so I’ll share the lessons I learned while vibe coding under real pressure.

Round 1: Getting Hands On

There were two rounds. The first was a demo round where we had to build something using the AI tools and get familiar with the workflow.

Since I had already worked with AI Studio while building my portfolio in the New Year, New Me Dev Challenge, I was excited to try Antigravity, especially because it has a VS Code like feel.

What immediately stood out in Antigravity was its planning first approach.

The moment your prompt hits, it:

• analyzes the request
• creates a plan
• executes tasks step by step

Even better, I could modify the plan according to my needs. That feature really stood out to me because it felt like AI was finally doing what it’s supposed to do: plan first, execute second.

My First Build (and Early Confidence)

In the first round, I built a game app using Antigravity.

I did hit several roadblocks, but my previous experience with AI Studio helped me move faster. The first iteration was surprisingly good.

• Game sprites were generated using Nano Banana
• Characters also came out quite well
• Initial deployment worked

At that moment, I felt pretty confident. And then… I hit the wall.

Where Things Started Breaking

The more iterations I tried to push through Antigravity, the more issues started appearing.

I consider myself a beginner vibe coder, and one thing I’ve learned is:

The more you work with prompts, the more your prompting style evolves.

So I reset my approach, started fresh, and tried giving clearer prompts.

But under time pressure, hallucinations started creeping in.

The biggest issues I faced were:

• Uploading code from Antigravity to GitHub
• Deploying to Google Cloud Run
• CORS related problems
• Inconsistent executions

For some participants, the magic worked smoothly. For me not so much.

Still, I pushed through, submitted the prototype, and scored 46% overall.

Not great. But very educational.

The Reset Between Rounds

During lunch, instead of stressing, I cooled off and started talking to other developers.

This turned out to be extremely valuable.

I learned:

• how others were structuring prompts
• how they handled hallucinations
• where they were getting blocked

That peer feedback helped me rethink my approach for Round 2.

Round 2: Changing Strategy

For the main round, I made a strategic shift.

Instead of forcing Antigravity, I moved back to AI Studio, mainly because:

• deployment was more predictable
• GitHub integration felt smoother
• I could move faster under time pressure

I also simplified the scope moving from a 3D game to a 2D game and refining my prompts more carefully.

This time, the system responded much better.

Submission Attempts and Reality Check

We had four submission attempts.

Attempt 1: 50%
Criteria included:

• Code Quality
• Security
• Efficiency
• Testing
• Accessibility
• Google Services

My weak areas were clearly Security and Google Services.

Since I was relying heavily on AI Studio, I wasn’t fully aware of all the security gaps I might be hitting.

Attempt 2: Still 50%

I thought I had improved the code significantly but the score didn’t move. That was a reality check.

Attempt 3: 62.67%

This time I changed tactics:

• asked the model to refactor more carefully
• focused on structure
• tested more deliberately

Glitch Hunt
This is the game I developed and submitted. Making it a newer version of the classic DuckHunt. It's still is in prototype phase.

I still didn’t make the top 10 but the learning curve was massive.

I also reviewed other teams’ web games and noticed a common theme: Everyone was fighting hallucinations and AI limitations in different ways.

Lessons I’m Taking Forward

1. Plan before you vibe code: Don’t jump straight into prompting without thinking through scope and data.

2. Stay flexible with tools: Sometimes switching platforms saves more time than forcing one tool.

3. Prompt clarity improves with iteration: The more precise the prompt, the better the output.

4. AI will hallucinate expect it: Save versions frequently and be ready to roll back.

5. Commit and deploy frequently: Version history saved me multiple times.

6. Peer feedback is underrated: Talking to other builders gave me insights I wouldn’t have found alone.

7. Different models excel at different tasks: I used GPT for prompt generation and Gemini for data heavy reasoning.

8. Don’t over iterate blindly: At one point I kept prompting without validating outputs, which created more confusion than progress.

9. AI tools still need developer judgment: Even when output looks correct, manual review is essential.

10. Time pressure exposes prompt quality: Clear prompts saved far more time than clever but vague ones.

This hackathon didn’t just test my ability to build with AI. It tested how clearly I could think under pressure. I’m still learning, still breaking things, and still refining how I work with AI tools.

Vibe coding looks fast from the outside, but in reality, the quality of prompts, planning discipline, and iteration strategy makes a huge difference.

Would love to hear from others what was the biggest roadblock you faced while vibe coding?