DEV Community: Prince Sharma

Slow & Steady: A Personal Agent That Takes the Busywork Off Your Plate

Prince Sharma — Thu, 22 Oct 2026 17:12:17 +0000

Slow & Steady: A Personal Agent That Takes the Busywork Off Your Plate

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

I built Slow & Steady, a privacy-first personal productivity assistant designed to help people spend less time on boring digital tasks and more time on what matters.

We all have small tasks that we keep putting off: reading long group chats, organizing messy folders, and trying to relax after a busy day. Slow & Steady brings these everyday tasks together in one simple, calm interface.

The project includes three main tools:

Chat Summary: Turns a conversation into a short recap with possible action items and important dates.
Inbox Tidy: Creates a suggested folder structure and file organization plan to help reduce digital clutter.
Wind-down Companion: Provides calming prompts and a short breathing exercise to help users relax.

It also includes a daily checklist to make small tasks easier to manage.

My goal is simple: let technology handle the boring parts so people can take life a little slower.

Code

Project: Slow & Steady — Personal Productivity Agent

The project is built using three main files:

index.html — website structure and content
style.css — responsive styling and visual design
script.js — navigation, chat recap logic, file organization suggestions, checklist interactions, and breathing exercise

The interface is designed to be simple, responsive, and easy to use without installing additional dependencies.

How I Built It

I built the first prototype using HTML, CSS, and JavaScript.

I wanted to start with a lightweight application that could run directly in a browser without requiring an API key or a complicated setup.

The current version demonstrates the main workflows using JavaScript-based logic. For example, the chat summarizer identifies possible action items and dates, while the inbox tool generates a suggested organization plan using sample files.

Important: The current prototype does not yet use a real AI model. Integrating an open-weight model through a local inference runtime such as Ollama is the next step toward making the assistant genuinely AI-powered.

My intended architecture is to use an open-weight model for tasks such as summarizing conversations and understanding natural-language requests, while keeping personal data on the user's machine wherever possible.

Why Does Open Innovation Matter?

Open innovation matters because personal productivity tools may handle private information, including conversations, documents, and daily routines.

Closed AI APIs can be useful, but they may require sending data to an external service and can introduce usage costs or platform restrictions.

An open approach gives developers more control over how models are deployed, where inference happens, and how the application can be modified.

For Slow & Steady, open-weight AI could make it possible to:

Run supported models locally instead of relying entirely on a hosted AI API.
Reduce recurring API costs.
Customize the assistant for specific everyday tasks.
Inspect and improve the application's code.
Give users greater control over their data.

I believe useful AI should not always require an expensive service or a complicated setup. Open innovation makes it easier for more developers to experiment, learn, and build tools that solve real problems.

The Lazy Payoff

The idea behind Slow & Steady is to reduce the small amounts of effort that add up throughout the day.

Instead of manually reviewing a long conversation, users can get a quick recap. Instead of deciding how to organize a messy folder from scratch, they can start with a suggested plan. And instead of endlessly scrolling at night, they can use a simple wind-down routine.

The current version is a prototype, so I have not yet measured real-world time savings. My next goal is to test it with real users and measure how much time it saves.

What I Learned

Building this project helped me explore how a small productivity tool can be designed around privacy, simplicity, and user control.

It also helped me understand the difference between building an AI-friendly interface and actually integrating an AI model. The next stage is to connect a local open-weight model and evaluate its results on real tasks.

Final Thoughts

Slow & Steady is built around one idea: you should not have to spend your whole day managing the little things.

I want to keep improving it into a useful, local-first personal assistant that helps people work a little less, worry a little less, and enjoy more of their time.

Sometimes, the smartest tool is the one that gives you permission to slow down.

Prize Categories

[Add the applicable partner categories from the official challenge rules here.]

Built with HTML, CSS, and JavaScript for Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

PaperPilot: A Privacy-First Document Assistant for Freelancers

Prince Sharma — Wed, 14 Oct 2026 08:46:22 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

PaperPilot is a document management web application designed for freelancers and small businesses.

Freelancers often waste time organizing invoices, receipts, and other business documents. PaperPilot aims to make this process easier through a simple, professional dashboard.

Features

📄 Upload PDF, PNG, JPG, and TXT files.
📁 Organize documents into invoices, receipts, and other categories.
🔎 Search and filter document records.
📊 View document statistics on the dashboard.
🔒 Store document metadata locally in the browser.
🗑️ Delete individual records or clear the library.

The project is built with HTML, CSS, and JavaScript. It is designed to help freelancers manage their paperwork without requiring a paid API.

The project contains three main files:

index.html — Website structure
style.css — Styling and responsive design
script.js — Document management and interactions

How I Built It

I built PaperPilot using HTML, CSS, and vanilla JavaScript.

HTML provides the application structure, CSS creates a responsive interface, and JavaScript powers document categorization, searching, filtering, and deletion.

Browser local storage keeps document metadata available between sessions. The current prototype does not upload files to a server or require an external API key.

The next development step is integrating an open-weight AI model running locally to extract invoice information and summarize expenses.

Why Does Open Innovation Matter?

Open innovation gives developers and small businesses more control over their technology.

For PaperPilot, locally running open-weight AI could help freelancers extract invoice details and organize expenses without sending sensitive documents to a third-party AI service.

It could also reduce dependence on paid APIs and give users more flexibility over their costs, privacy, and model choices.

My goal is to develop PaperPilot into an affordable, privacy-focused assistant that helps freelancers spend less time on repetitive paperwork and more time growing their businesses.

My Agent Session

Not applicable to the current version.

My First User

This project is currently a prototype. I plan to share it with freelancers and small business owners to collect feedback and understand which document management features would be most useful.

Prize Categories

Side Hustle

GreenBuddy AI: Your Open-Source AI Companion for Touching Grass

Prince Sharma — Sat, 10 Oct 2026 08:11:17 +0000

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

What I Built

I built GreenBuddy AI, an outdoor adventure companion designed to help people spend less time on screens and more time in nature.

GreenBuddy AI helps users discover outdoor activities, take daily nature challenges, track their outdoor progress, and generate personalized outdoor adventure plans.

The project includes:

Outdoor activity suggestions
A 20-minute screen-free challenge timer
An outdoor activity progress tracker
An AI-powered adventure planner
A responsive interface built with HTML, CSS, and JavaScript

The goal is simple: use technology to encourage people to disconnect from their screens and reconnect with the real world.

Demo

I built and tested the project locally.

Screenshots and a video demonstration can be added here.

Code

The project uses three separate frontend files:

index.html — Website structure
style.css — Responsive styling and user interface
script.js — Timer, activity tracking, and AI integration

GitHub repository: [Add your GitHub repository link here]

How I Built It

I built GreenBuddy AI using HTML, CSS, and JavaScript.

For the AI component, I chose Ollama to run an open-weight language model locally on my computer.

The AI planner is designed to generate personalized outdoor activity plans based on the user's mood, available time, and preferred location.

The project is designed to use Gemma through Ollama. The AI functionality requires the local model and Ollama service to be installed and running.

The timer and progress tracker work directly in the browser using JavaScript.

Why Does Open Innovation Matter?

Open innovation makes GreenBuddy AI more accessible, flexible, and privacy-friendly.

By using an open-weight model through Ollama, I can experiment with local AI inference instead of depending on a paid, closed AI API.

This approach offers several advantages:

Privacy: Prompts can be processed locally instead of being sent to a third-party AI provider.
Flexibility: I can experiment with different compatible models.
Accessibility: Local inference can avoid per-request API charges.
Learning: Working with open AI tools helps me understand how AI applications work beyond simply calling a hosted API.

The project also demonstrates that AI can be used to encourage healthier offline habits instead of keeping people glued to their screens.

My goal is to make the screen the starting point of an outdoor adventure, not the destination.

My Agent Session

Optional: Add a DevRelay agent session if available.

Prize Categories

Hacktoberfest Open-Source AI Challenge — Week 1: Touch Grass.

Thanks for checking out GreenBuddy AI! 🌿

Hello DEV Community! Excited for Hacktoberfest 2026

Prince Sharma — Mon, 05 Oct 2026 14:38:49 +0000

Hello everyone!

I'm Prince, a Computer Science Engineering student and a beginner developer interested in AI, web development, and open-source projects.

This is my first post on DEV, and I'm excited to participate in Hacktoberfest 2026! 🚀

I'm looking forward to learning, building projects, contributing to open source, and connecting with other developers during Hacktoberfest.
Happy Hacktoberfest!

hacktoberfest #opensource #webdevelopment #ai #beginners