I Built an AI That Teaches You to Notice the World, Not Stare at a Screen

Rittik Chakraborty — Sun, 11 Oct 2026 14:26:27 +0000

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

What I Built

Observation Coach — A little less screen. A little more world.

Most AI applications try to keep you engaged with your screen. I wanted to build something that does the opposite: an AI coach that helps you put your phone away and pay closer attention to the world around you.

Observation Coach — Live Preview

The idea is simple: AI should teach you how to observe, rather than observe everything for you.

Here's how it works:

Choose an exercise: Pick a short observation session lasting 5, 10, 20, or 30 minutes.
Step away: The app invites you to put your phone away and explore your surroundings.
Notice something real: Return and describe a detail you actually observed.
Reflect with AI: The coach asks a thoughtful follow-up question based on your description.
Build the skill: Receive an adaptive next exercise designed to help you develop your observation skills over time.

Instead of identifying objects through a camera, generating endless challenges, or turning everything into a competition, Observation Coach focuses on attention, description, comparison, change, inference, and deeper observation.

It's designed for anyone who wants to reconnect with their surroundings, become more mindful of everyday details, or simply spend less time staring at a screen.

The goal isn't to make people spend more time with AI. It's to make them need AI less.

Demo

Product Walkthrough:

https://youtu.be/KArn5bRtpeI

Code Walkthrough:

https://youtu.be/vQHZ7amHMTo

Try the Live Preview:

https://observation-coach.vercel.app

Code

The project is open source:

https://github.com/devrittik/observation-coach

Built with Next.js, TypeScript, Tailwind CSS, and MongoDB.

How I Built It

I built Observation Coach with a focus on modular architecture, privacy, and the flexibility to use open-weight models locally or through a hosted inference provider.

The technology stack

Frontend and application: Next.js App Router, TypeScript, and Tailwind CSS.
Database: MongoDB for user accounts, sessions, saved observations, and progress.
AI integration: A provider abstraction that supports local inference and hosted OpenAI-compatible APIs.
Local inference: Qwen 3B Instruct in GGUF format, downloaded from Hugging Face and run through llama.cpp.
Hosted inference: Qwen 27B Instruct through Groq.
Validation: Structured model responses are validated before being used by the application.

Why the AI is a coach, not an answer machine

The interesting part of this project isn't simply generating a response to a user's observation.

The coach needs to meet the user where they are. If someone notices only a basic detail, the AI should help them explore it further rather than immediately provide an elaborate interpretation.

The application uses structured prompts and validated responses to support short reflections, follow-up questions, and adaptive exercises. A separate progression system helps determine what the user can practise next.

Local AI and hosted AI

I wanted the project to be adaptable rather than permanently tied to one AI provider.

The local setup uses an instruction-tuned Qwen model in GGUF format through llama.cpp. For hosted inference, the application supports an OpenAI-compatible API, with Qwen 27B Instruct through Groq as my intended hosted configuration.

This separation means the application can support different inference environments without requiring a complete rewrite of its AI integration.

The project also includes a guided demo mode, so people can explore the observation workflow without requiring a working AI API key.

Why Does Open Innovation Matter?

For Observation Coach, open innovation is not just a way to reduce API costs. It changes where and how the application can be used.

1. AI that can work offline

With a local application, a local database, and a local open-weight model, the experience can work without an internet connection once everything is installed and running.

That makes the concept useful even in places with limited or unreliable connectivity. It also means the user doesn't have to depend on a remote AI service just to practise observing their surroundings.

2. Privacy and control over personal observations

An observation can be personal. People might write about their surroundings, emotions, memories, or everyday experiences.

Running inference locally allows those observations to remain on the user's machine rather than being sent to an external AI provider. This is an important option for a product built around personal reflection.

The hosted version is a practical alternative, but local inference gives users more control over their data.

3. Freedom to experiment and switch models

Open-weight models let developers experiment with different model sizes, prompts, and inference setups.

A smaller model can be useful for resource-constrained machines, while a larger hosted model can offer another option when local hardware is insufficient. This flexibility is especially valuable when building a project that should remain accessible to people with different hardware and budgets.

4. Technology that encourages people to disconnect

The most important design decision is that the AI is not supposed to become another reason to stay online.

Observation Coach deliberately keeps the interaction short. It gives the user an exercise, steps aside, and waits for them to return with something they actually noticed.

For me, that's the real point of the Touch Grass challenge: using AI to help people reconnect with the world, rather than creating another experience that competes for their attention.

My Agent Session

I didn't use DevRelay for this project, so I don't have a DevRelay session to share.

The code and implementation details are available in the GitHub repository, and the code walkthrough provides another way to explore the project.

Prize Categories

Best Use of MongoDB Atlas

Submission Type

Individual submission.

Portfolio

https://devrittik.com

Built for Hacktoberfest 2026 — Open-Source AI Challenge, Week 1: Touch Grass.

devchallenge #hf26challenge #hacktoberfest #opensource #ai #nextjs #mongodb #llama.cpp

Dukaandaar AI — An Open-Source AI Assistant for Small Businesses

Rittik Chakraborty — Mon, 05 Oct 2026 06:57:22 +0000

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

What I Built

I built Dukaandaar AI for my friend Suman Mandal, who works as an accountant handling inventory-related operations.

The idea started from seeing how much day-to-day business information can involve repetitive entries, calculations, inventory tracking, sales, purchases, and expenses.

I wanted to build something that could make these tasks easier and more natural to interact with.

Dukaandaar AI is an AI-powered business management application for small shops and businesses. It provides features for:

📦 Inventory management
🛒 Sales
📥 Purchases
💰 Expenses
📊 Business reports
📉 Losses and adjustments
🤖 Natural-language interaction with business data
🎙️ Voice-based interaction

For example, instead of manually searching through the application, a user can ask:

"How many units of this product are left?"

or:

"How much did I spend this month?"

The project started as something I wanted to build for one real person, and then I decided to stretch the idea into a more complete tool that could potentially be useful for other small businesses as well.

Demo

drive.google.com

Code

Repository: https://github.com/devrittik/dukaandaar-ai

Live

URL: https://dukaandaar-ai.vercel.app

How I Built It

Dukaandaar AI is built with:

React
Node.js
Express
MongoDB
REST APIs
AI/LLM integrations
Local AI components
Speech-to-text / voice interaction
Authentication and application logic

A major design goal was to support both local/private and hosted deployments.

For users who want maximum privacy, the application can be run locally with local AI components, allowing business data to remain on their own machine.

For users who prefer convenience and remote access, the application can also be deployed as a hosted application.

The AI is not intended to be just a chatbot sitting beside the application. The goal is to make AI an actual interface for interacting with structured business information.

Why Does Open Innovation Matter?

For a small business application, privacy can be extremely important because inventory, sales, purchases, and financial information can be sensitive.

Open-source AI and local inference make it possible to build an AI-powered application where users can choose to keep their data and inference local instead of being completely dependent on a closed third-party API.

It also gives developers more control over the AI layer. Models and inference approaches can be changed or upgraded without having to redesign the entire application around a single proprietary provider.

For Dukaandaar AI, that flexibility is especially useful because the project supports both fully private/local usage and hosted usage.

My Agent Session

This project was not built using DevRelay, so I don't have an agent session to include.

DEV Community: Rittik Chakraborty

I Built an AI That Teaches You to Notice the World, Not Stare at a Screen

What I Built

Demo

Code

How I Built It

The technology stack

Why the AI is a coach, not an answer machine

Local AI and hosted AI

Why Does Open Innovation Matter?

1. AI that can work offline

2. Privacy and control over personal observations

3. Freedom to experiment and switch models

4. Technology that encourages people to disconnect

My Agent Session

Prize Categories

Submission Type

Portfolio

https://devrittik.com

devchallenge #hf26challenge #hacktoberfest #opensource #ai #nextjs #mongodb #llama.cpp

Dukaandaar AI — An Open-Source AI Assistant for Small Businesses

What I Built

Demo

Code

Live

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

Portfolio

devchallenge #weekendchallenge #hf26challenge