DEV Community: Vaishnavi Pophalkar

Plan A Date 🌿 — From Endless Scrolling to a Day Worth Remembering

Vaishnavi Pophalkar — Sat, 10 Oct 2026 14:55:38 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

What if planning a memorable day took less time than actually experiencing it?

We often spend more time scrolling through cafés, checking places, comparing activities, and figuring out what to do than enjoying the time we spend with people. I wanted to build something that changes that.

Meet Plan A Date — an AI-powered outing planner that turns your available time, mood, budget, interests, and location into a personalized plan for spending meaningful time with someone.

And no, a “date” doesn't have to be romantic. ❤️

It could be a café-hopping afternoon with your best friend, a creative workshop with a sibling, a peaceful nature walk with your family, or an adventurous day with someone you're getting to know.

Here's what makes Plan A Date different:

🌱 Plans around your time: Whether you have 45 minutes or an entire day, the itinerary is designed around your available time.

📍 Real-world discovery: SerpApi helps discover real places, while location information helps make recommendations relevant to where you're going.

✨ Personalized itineraries: Gemma helps organize candidate activities into a coherent outing tailored to your companion, mood, budget, and schedule.

🍒 Cherry on Top: Every plan can end with a thoughtful gesture, a little surprise, or a small memory-making idea.

🌿 Touch Grass Mode: Once your plan is ready, switch to a minimal interface focused on your next stop, so you can spend less time on your phone and more time being present.

📖 Remember the day: A memory-journaling concept helps you preserve the moments worth remembering.

The guiding idea is simple:

Plan → Go Outside → Experience → Remember

The screen should be the shortest part of the experience.

Demo

Try Plan A Date:
Live Demo

Code

Source Code:
GitHub Repository

How I Built It

I built Plan A Date with a simple principle in mind:

Search discovers reality. AI organizes reality.

The application combines a modern React and TypeScript interface with a server-side API layer.

Frontend: React, TypeScript, Tailwind CSS, Lucide icons, and Leaflet for the interactive map.

Backend: Node.js and Express for server-side API routes.

Open-weight AI: Google Gemma, accessed through the Gemini API using the @google/genai SDK.

Real-world discovery: SerpApi's Google Local search capabilities to discover relevant venues.

Location and maps: Browser geolocation, OpenStreetMap-based reverse geocoding, and Leaflet.

Fallback handling: A fallback venue catalog helps the experience remain usable when live discovery is unavailable, with fallback results distinguished from live search results.

Gemma is intended to do more than produce a generic list of suggestions. It helps turn available venue candidates into a plan that considers the person you're with, the mood you're looking for, your time constraints, and your budget.

The interface then presents that plan as a visual journey, rather than another chatbot conversation.

I focused on making the experience feel like a lifestyle and discovery product: ask a few meaningful questions, receive a plan, and head outside.

Why Does Open Innovation Matter?

For Plan A Date, open innovation is about making AI-powered experiences more adaptable, accessible, and developer-driven.

AI should organize real information, not invent reality.

A convincing AI-generated itinerary is not useful if its café doesn't exist or its activity is unavailable. Combining live place discovery with AI-generated planning helps separate finding real-world options from deciding how those options fit together.

Open-weight models create room to experiment.

Gemma provides an open-weight model option for the personalization layer. Open-weight models can give developers more flexibility to experiment with model behavior and, where supported by the model and deployment setup, explore self-hosted or local inference rather than relying exclusively on closed models.

Plan A Date currently accesses Gemma through the Gemini API; it does not claim to run inference locally.

Useful AI should help people reconnect with the real world.

AI applications often compete for more of our attention. I wanted to explore the opposite: using AI to reduce decision fatigue, make planning easier, and help people step away from their screens.

The goal isn't to keep someone chatting with an AI. It's to help them make a plan, close the app, and create a memory with someone they care about.

That is what “Touch Grass” means to me. 🌿

My Agent Session

Prize Categories

Best Use of Gemma — for the open-weight model's role in personalized itinerary composition.

Best Use of SerpApi — for discovering real-world places that inform the generated outing.

Vaishnavi

FinTrack-AI : Turning my Family's Excel Sheets into an AI Financial Companion

Vaishnavi Pophalkar — Sun, 04 Oct 2026 15:34:32 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

What I Built
I built FinTrack AI for my father and uncle. ❤️

My father and uncle manage their financial records using Excel sheets. While Excel is great for maintaining records, manually entering transactions, organizing data, calculating summaries, and trying to understand spending patterns can become repetitive and time-consuming.

So I wanted to build something that would work with the way they already manage their finances, instead of making them learn an entirely new system.

That's how FinTrack AI was born.

FinTrack AI is a local-first AI-powered finance tracker where users can simply upload their existing Excel or CSV financial data and start working with it.

Instead of manually going through rows and formulas, they can:

📂 Upload their existing Excel/CSV files
📊 Automatically organize and analyze their transactions
💰 View financial summaries and spending insights
📈 Explore their expenses through a dashboard
🤖 Ask questions about their financial data using AI
🧠 Get AI-generated explanations and summaries
📥 Export their processed financial data back to Excel
💾 Keep their financial information locally

For example, instead of manually searching through an Excel sheet, they can ask questions such as:

"Where did I spend the most this month?"

"What are my biggest expense categories?"

"Give me a summary of my spending."

"What are my major transactions?"

The goal is simple:

Take the Excel sheets they already use and make them much easier to understand.

I didn't want to build another complicated finance application that required them to completely change their workflow.

I wanted to build something that fits into it.

Upload → Analyze → Ask → Understand → Export

That's FinTrack AI.

Demo

🎥 Demo Video: Video Link

The demo will show the complete workflow of FinTrack AI:

Upload an existing Excel/CSV file
Import and process the financial transactions
View the financial dashboard and summaries
Ask FinTrack AI questions about the data
Receive an AI-generated explanation
Export the financial data back to Excel

Code

💻 GitHub: Github Repository
The complete source code is available in the repository, including the Streamlit application, financial data processing, SQLite database integration, Excel/CSV handling, and local Gemma + Ollama integration.

How I Built It

FinTrack AI is built as a local-first financial application, combining traditional data processing with an open-weight AI model.

🛠️ Tech Stack
Python — core application logic
Streamlit — user interface
SQLite — local financial data storage
Pandas — financial data processing and analysis
openpyxl — Excel file handling
Ollama — local AI model runtime
Gemma 3 1B — open-weight AI model
🤖 How Gemma is actually used

The AI component is powered by Gemma 3 1B, running locally through Ollama.

FinTrack AI does not simply send the user's financial information to a cloud AI API.

Instead, the application runs Gemma locally through Ollama.

The local inference flow is:

User's Financial Data → Python/Pandas Analysis → Relevant Financial Context → Gemma 3 1B → Natural-Language Explanation

Python and Pandas handle the actual numerical processing and financial calculations.

Gemma's role is to take the resulting financial information and make it easier for a human to understand through natural-language explanations and summaries.

Ollama provides the local runtime through which the application communicates with Gemma.

This was an important part of the project because I wanted to understand how an application can be built around an open-weight model running locally, rather than treating AI as a black-box cloud API.

🔒 Local-first by design

Financial information is sensitive.

Since this project was built for my own family, I wanted privacy to be a meaningful part of the architecture.

The AI inference happens locally through Ollama, and the financial data can remain on the user's machine rather than requiring a cloud AI service.

Why Does Open Innovation Matter?

This project is a great example of why I think open innovation matters, especially for applications dealing with personal data.

If I had built FinTrack AI entirely around a closed AI API, the AI portion would essentially be:

Send financial information → External API → Receive response

Using an open-weight model changes that possibility.

With Gemma 3 1B + Ollama, I can run the AI locally and control how the financial information is processed and provided to the model.

That gives me the freedom to:

Run AI locally
Experiment with an open-weight model
Control the context given to the model
Decide how financial calculations and AI explanations interact
Build without requiring a proprietary AI API
Learn how local AI inference works in a real application

For a financial application, this is especially meaningful because the data belongs to the user.

Open-weight AI allowed me to explore a model that isn't just something I call through a remote endpoint — it can actually become part of the application running on the user's own machine.

It also made this project a much better learning experience for me.

I didn't just want to build an application that uses AI.

I wanted to understand how to build an application around an open AI model.

Prize Categories

Best Use of Gemma

Team

Built by: Vaishnavi pophalkar

❤️ Why this project matters to me

FinTrack AI started with a very simple problem at home.

My father and uncle were already maintaining their financial records in Excel.

I didn't want to tell them:

"Stop using Excel and learn this completely new finance app."

Instead, I thought:

"What if I build something that works with the Excel sheets they already have?"

That became the foundation of FinTrack AI.

Now, instead of manually maintaining and analyzing everything, they can upload their existing data, understand it through dashboards and AI, ask questions naturally, and still get their data back as an Excel file whenever they need it.

For me, that's what Build for a Friend is about.

Not just building something technically impressive.

Building something for a real person you care about, around a problem you've actually seen. ❤️