EventPilot AI 🦥 — Less Planning Chaos, More Celebrating | Hacktoberfest Week 3
What if we could make that process a little less exhausting?
That's the idea behind EventPilot AI — an AI-assisted event-planning companion built to turn scattered ideas into a more organised starting point, so you can spend less time managing details and more time enjoying the occasion.
What I Built
EventPilot AI is designed for students and small-to-medium event organisers who want to plan something memorable without getting overwhelmed by the logistics.
It focuses on three everyday planning problems:
- 📝 Planning: Organise an event idea, guest count, budget, and preferred atmosphere into a structured starting point.
- 💸 Budgeting: Calculate a 7% contingency reserve and estimate the budget per guest instead of doing repetitive calculations manually.
- ✅ Staying organised: Keep planning considerations such as timelines, checklists, vendor details, and next steps together.
The philosophy is simple: less planning chaos, more room for the celebration.
Rather than making organisers start with a blank page, the goal is to help them get moving with a plan they can review, customise, and improve.
Demo: https://eventpilot-8z66.onrender.com/
The current project includes an interactive planner preview that demonstrates the budgeting workflow.
A public deployment or video walkthrough has not been verified for this submission, so I don't want to link an unrelated demo or misrepresent the preview as a live AI-powered application.
Code
💻 GitHub repository: https://github.com/riyanshika7/EVENTPILOT
The project is built with a lightweight web stack, with an emphasis on maintainability, practical calculations, and a clear separation between the interface and backend.
How I Built It
The current project architecture uses:
- Python and FastAPI for backend routes and application logic.
- HTML, CSS, and JavaScript for the frontend.
- SQLite for data storage.
- Pytest for automated testing.
- Gemma integration as the intended open-weight AI component, with live endpoint connectivity still requiring verification.
One important design choice is to keep calculations deterministic wherever possible. For example, the contingency reserve and estimated cost per guest should be calculated by application code rather than left to an AI model to guess.
AI can help with planning suggestions, but arithmetic should remain arithmetic.
I'm also working on the reliability details that matter beyond a polished interface: configuration, input validation, useful error messages, accessibility, and deployment readiness.
Why Does Open Innovation Matter?
Open innovation makes it possible to experiment, learn, and build useful tools without treating AI as a closed black box.
Open-weight models such as Gemma can give developers more flexibility to explore model behaviour, adapt integrations, and choose deployment approaches that fit their constraints. Open-source frameworks also make it easier for other developers to inspect the surrounding application and contribute improvements.
For a student developer, that freedom matters. It creates room to learn by building, understand the moving parts, and improve a project incrementally.
The important distinction is that using an open model is only part of the story: the integration must actually work, and the application around it must be reliable enough to be useful.
That's the direction I'm working toward with EventPilot AI.
The Lazy Payoff 🦥
The idea is to eliminate some of the repetitive work that makes event planning tiring.
For example, given a budget of ₹8,000 and 30 guests, the planner can calculate:
- Contingency reserve (7%): ₹560
- Remaining planned-cost budget: ₹7,440
- Approximate budget per guest: ₹267
That means fewer manual calculations before you even start refining the event.
The bigger payoff would come from helping organisers move from an idea to a practical checklist without having to assemble everything from scratch. I haven't measured real-world time savings yet, so I'd rather test the workflow with an actual organiser than invent a productivity statistic.
Slow and steady — one useful improvement at a time. 🌱
Building EventPilot AI has reminded me that useful software isn't always about adding more features. Sometimes it's about removing friction, making a confusing process clearer, and giving people a little more breathing room.
The vision is simple: your people, your moment, and a plan that gets you there. ♡
Prize Categories
EventPilot AI is intended to make event planning less stressful by helping people organise their plans and budgets.
Categories I'm considering:
- Best Use of Gemma ($200) — for the open-weight AI integration, provided the Gemma model is successfully connected and meaningfully powers the project.
- Best Use of Render ($200) — if EventPilot AI is deployed on Render and the deployed application demonstrates the project working.
- Best Use of Sentry Agent Tracing ($100) — if Sentry Agent Tracing is configured and meaningfully used to trace the AI workflow.
I'm aiming to make open-source AI a meaningful part of EventPilot AI, not just an add-on. I'll include only the categories supported by the final implementation.
The project is also eligible for consideration for the overall winner prize if it meets the challenge requirements.
Top comments (0)