Built “Event Buddy AI” in a day for PromptWars (Google Antigravity + Cloud Run)

Source: Dev.to

The problem I wanted to solve

• “Where is Hall A or Hall B?”
• “Where’s the help desk or food court?”
• “What can I attend next that actually matches my interests?”
• “I only have 30 minutes. What should I do?”

Most event apps are either too heavy or don’t give quick answers. I wanted a lightweight assistant that feels like asking a friend who knows the venue and schedule.

What I built – Event Buddy AI

• Ask venue questions (halls, food, washrooms, help desk).
• Get a suggestion for the next session based on interests (AI, design, startup, etc.).
• Use a few sample questions if the user doesn’t know what to type.
• See small info cards for halls and key locations.

It’s a focused helper that answers “What do I do now and where do I go?” rather than a full‑blown enterprise product.

Tech stack

• Google Antigravity – planning and generating most of the code.
• Python + Flask – backend.
• HTML, CSS, JS – simple, responsive UI.
• Local JSON file – stores sample event data (halls, sessions, locations).
• Google Cloud Run – deploys the app and provides a public URL.

Antigravity helped quickly scaffold the project structure, generate the Flask app, and prepare it for Cloud Run, letting me focus on logic and UX.

How it works

1. The user types a question or clicks a sample question.
2. The backend performs simple intent and keyword matching on the question.
3. It returns either:
   • A direct answer (e.g., “Hall A is on Level 1 near the main entrance”), or
   • A recommended session (e.g., “You like AI? Attend ‘Intro to GenAI’ at 3:00 PM in Hall B.”)
4. The UI displays the answer clearly, with an option to ask another question.

No heavy databases, no complex authentication—just a fast conversational layer over structured event data.

Challenges I hit

• Cloud Run permissions
• Time management

What I learned

• AI tools like Google Antigravity are powerful when given a clear prompt and realistic scope.
• Cloud Run makes it easy to go from a local Flask app to a shareable URL.
• A small, well‑explained project with clean UX and a live demo is far more valuable than an unfinished “big idea.”

Links

• Repository:
• Live demo on Cloud Run: