DEV Community: Naila Akram

Building Astuto Next

Naila Akram — Sun, 01 Nov 2026 05:23:40 +0000

🎃 Building Astuto Next – A Public Feedback Board with AI-Powered Duplicate Detection

I've been working on a new project called Astuto Next, inspired by the idea of making product feedback easier to share, discover, and manage.

The basic problem I wanted to explore was this: when users have ideas for improving a product, their suggestions can get scattered across different platforms. Sometimes, multiple people even suggest the same feature without knowing that someone else has already requested it.

So, I wanted to build a simple platform where people can share ideas, discover existing requests, and vote for the features they would actually like to see.

That's how Astuto Next started! 💜

✨ What is Astuto Next?

Astuto Next is a public feedback board where users can explore companies, submit feature requests, and support ideas through community voting.

Instead of feedback getting lost, the platform brings suggestions together in one place.

🚀 Features I've built

🏢 1. Company Feedback Boards

Users can add companies and explore their feedback boards. Each company has its own space where people can share suggestions and view existing requests.

💡 2. Feature Requests

Users can submit their ideas by adding a title and description. This makes it easier for others to understand the problem and the improvement being suggested.

👍 3. Community Voting

Not every suggestion needs to be submitted again. Users can browse existing ideas and vote for the ones they want companies to consider. This also helps popular requests get noticed.

🤖 4. AI Duplicate Finder

This is one of the features I was particularly excited to experiment with!

Before submitting a new request, users can ask AI to check whether a similar suggestion already exists for that company.

I'm using a local Ollama model (Llama 3.2 1B) for this. It compares the new request with existing suggestions and identifies possible matches.

If a similar request is found, users can support the existing idea instead of creating another one.

🎃 5. Halloween-inspired Interface

I also experimented with the visual design, giving the platform a dark Halloween-inspired theme with purple and orange colours.

🛠️ Tech Stack

Here are the technologies I used:

HTML – Page structure
CSS – Styling and responsive design
JavaScript – Frontend interactions and API requests
Node.js – Backend runtime
Express.js – API routes and server
SQLite (better-sqlite3) – Storing companies and feature requests
Ollama + Llama 3.2 1B – Local AI integration

🧠 Challenges and What I Learned

This project was a good learning experience because I got to work on both frontend and backend functionality.

Some things I learned and explored while building it:

Connecting frontend actions with backend API routes.
Creating and managing database tables using SQLite.
Fetching and displaying data dynamically.
Implementing voting functionality.
Connecting a local AI model with an Express backend.
Handling API errors and debugging issues when the frontend and backend didn't communicate as expected.

The AI integration was especially interesting. Getting Ollama to respond successfully was one part, but making it compare feature requests correctly was another challenge.

I also learned that an AI feature needs proper testing rather than simply displaying an AI-generated response.

🔮 What's Next?

Astuto Next is still a work in progress, and I have more ideas for it.

Some improvements I'd like to explore include:

AI-powered feedback analysis to identify common topics.
Notifications when a feature request changes status.
Better ways for companies to interact with community feedback.
Improving duplicate detection and its accuracy.

💭 Final Thoughts

I started this project to explore how an existing open-source idea could be extended with AI and turned into something useful.

It wasn't just about adding AI to a website. I wanted to understand how it could solve an actual problem for users.

There were definitely a few debugging struggles along the way, but getting the different parts connected and working made the process worth it.

Github Repository - https://github.com/nailaAkr/astuto-nexxt

I'd love to hear your thoughts!

What other AI-powered features would you add to a public feedback platform?

Thanks for reading! 💜

JavaScript #NodeJS #AI #Ollama #WebDevelopment #SQLite #ExpressJS #BuildInPublic

🐛 ERRORBUDDY AI: YOUR PERSONAL DEBUGGING BUDDY, POWERED BY GEMMA

Naila Akram — Mon, 26 Oct 2026 03:34:07 +0000

Week 3 of Hacktoberfest 🚀 Building ErrorBuddy AI 🐛

Have you ever been coding, everything seems fine, and suddenly your terminal throws an error that makes you question everything? 😭

I've been there. Sometimes, the error message itself feels more confusing than the actual problem. And when you're still learning to code, figuring out what went wrong can take more time than writing the code in the first place.

That's what gave me the idea for ErrorBuddy AI.

I wanted to build something that could make debugging a little less frustrating, especially for beginners who are still trying to understand different errors and how to fix them.

🐛 So, what is ErrorBuddy AI?

It's an AI-powered debugging assistant where you can paste your coding error and get an explanation in simple language, along with a possible solution.

Instead of just looking at an error message filled with technical terms, the goal is to understand why the error happened and what you can do about it.

For this project, I'm using Gemma with Ollama to power the AI responses, along with Node.js and Express for the backend. I've also been working on the UI and exploring MongoDB Atlas for storing data.

The journey hasn't been completely smooth, though. 😅

I've had to deal with API errors, server issues, and figuring out how to get everything working together. There were moments when the request failed and I had to go back, check the code, and figure out what was wrong.

Ironically, while building a tool to explain errors, I ended up debugging my own project quite a bit. 😂

But honestly, that's also one of the things I enjoy about building projects. You don't always know the solution immediately, and sometimes you learn more from fixing something that went wrong than from getting everything right the first time.

I'm still working on ErrorBuddy AI, and there's a lot I'd like to improve, especially making the responses shorter, clearer, and more useful for someone who's just starting to code.

The idea is simple: debugging shouldn't feel like learning a whole new language. 💻

This is my Week 3 project for Hacktoberfest, and I'm excited to keep building, learning, and improving it along the way!

I'd love to hear what you think. What features would you want in an AI debugging assistant?

🔗 Live demo: https://errorbuddy.onrender.com
💻 GitHub Repository: https://github.com/nailaAkr/errorBuddy

Hacktoberfest #DEVCommunity #AI #WebDevelopment #OpenSource #Gemma #BuildInPublic

Google Photos + AI Storage Assistant

Naila Akram — Mon, 19 Oct 2026 05:46:10 +0000

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

What I Built

You know that notification you get on your phone saying your storage is almost full? I get it every few days, and honestly, it's annoying.

Whenever I see it, I open my gallery and start looking for photos I can delete. But then I find so many similar pictures, random screenshots, and photos I don't even remember saving. Sometimes I want to delete a photo, but I stop because I'm not sure if I'll need it later.

And the worst part is figuring out which photos are duplicates. Going through hundreds of pictures one by one just to free up some space feels like too much work.

That's where I got the idea for Google Photos + AI Storage Assistant.

I wanted to build something that could make managing photos easier. The idea is to have a photo gallery where I can browse my pictures, organize them into albums, save my favorites, and eventually get help from AI when I need to clean up my storage.

So far, I've built a Google Photos-inspired interface with a photo gallery, categories, favorites, an album suggestion interface, and an AI assistant.

Here's what it currently has:

A gallery to browse photos.
Categories like Travel, Nature, and Screenshots.
A favorites feature for important photos.
A suggested album interface where users can select photos.
An AI chat assistant that runs using a local AI model.
A storage management section that I'm working to improve.

It's still a prototype, and I know there's a lot more I want to add. Duplicate detection is one of the features I'd really like to build next because it would solve the exact problem that inspired this project.

My idea is simple: I want cleaning up a photo gallery to take less time and feel less stressful.

Demo

🎥 Demo video: https://youtu.be/8dFOMaO5un4

Code

💻 GitHub:
Repository Link - https://github.com/nailaAkr/ai-storage-manager

How I Built It

I used HTML, CSS, and JavaScript to build the frontend, and Node.js with Express for the backend.

For the AI assistant, I used Ollama with the Llama 3.2 (1B) model. I wanted to try using an open-source model locally instead of relying on a paid AI API.

Getting everything connected wasn't completely straightforward. I had to work through some issues with the backend and the AI model before I could get responses in my application.

This project gave me a chance to learn by actually building something instead of just following tutorials. I also got to understand how a local AI model can be connected to a web application.

Why Does Open Innovation Matter?

I'm still learning, and I want to be able to experiment with AI without worrying about API costs every time I try something new.

Using Ollama made that possible for this project. I could run the model on my own computer and experiment with integrating it into my application.

I also like the idea of using open-source tools because they give developers the freedom to learn, experiment, and improve their projects. I'd like to explore more privacy-friendly features as I continue working on this, especially since photos can contain personal memories.

What's Next?

There are a few things I'd love to add:

A way to find duplicate and similar photos.
Suggestions for photos that users might want to review or delete.
Search that lets users describe the photo they're looking for.
Better album suggestions.
More control over how personal photo data is handled.

I know these features will take more work, but they're the direction I'd like to take the project in.

My First User

Right now, I'm building this around a problem I face myself, so I'd love to know if other people struggle with the same thing.

Do you also get storage-full notifications all the time? How do you decide which photos to delete? And would you use an assistant that helps you find duplicates instead of checking everything manually?

I'd love to hear your thoughts!

Thanks for checking out my project. ❤️

Google Photos + AI Storage Assistant

Naila Akram — Sat, 17 Oct 2026 15:15:54 +0000

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

What I Built

You know that notification you get on your phone saying your storage is almost full? I get it every few days, and honestly, it's annoying.

And the worst part is figuring out which photos are duplicates. Going through hundreds of pictures one by one just to free up some space feels like too much work.

That's where I got the idea for Google Photos + AI Storage Assistant.

So far, I've built a Google Photos-inspired interface with a photo gallery, categories, favorites, an album suggestion interface, and an AI assistant.

Here's what it currently has:

A gallery to browse photos.
Categories like Travel, Nature, and Screenshots.
A favorites feature for important photos.
A suggested album interface where users can select photos.
An AI chat assistant that runs using a local AI model.
A storage management section that I'm working to improve.

My idea is simple: I want cleaning up a photo gallery to take less time and feel less stressful.

Demo

🎥 Demo video: https://youtu.be/8dFOMaO5un4

Code

💻 GitHub:
Repository Link - https://github.com/nailaAkr/ai-storage-manager

How I Built It

I used HTML, CSS, and JavaScript to build the frontend, and Node.js with Express for the backend.

For the AI assistant, I used Ollama with the Llama 3.2 (1B) model. I wanted to try using an open-source model locally instead of relying on a paid AI API.

Getting everything connected wasn't completely straightforward. I had to work through some issues with the backend and the AI model before I could get responses in my application.

This project gave me a chance to learn by actually building something instead of just following tutorials. I also got to understand how a local AI model can be connected to a web application.

Why Does Open Innovation Matter?

I'm still learning, and I want to be able to experiment with AI without worrying about API costs every time I try something new.

Using Ollama made that possible for this project. I could run the model on my own computer and experiment with integrating it into my application.

What's Next?

There are a few things I'd love to add:

A way to find duplicate and similar photos.
Suggestions for photos that users might want to review or delete.
Search that lets users describe the photo they're looking for.
Better album suggestions.
More control over how personal photo data is handled.

I know these features will take more work, but they're the direction I'd like to take the project in.

My First User

Right now, I'm building this around a problem I face myself, so I'd love to know if other people struggle with the same thing.

I'd love to hear your thoughts!

Thanks for checking out my project. ❤️