The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Title:AI-Powered Personal Tutor — 24/7 Learning Assistant
Short Description:
A full-stack AI learning assistant that acts as a personal tutor. Instantly answers questions, generates practice quizzes, and provides step-by-step solutions — built with Python, FastAPI, and Next.js.
Full Description:
An intelligent teaching agent that gives students personalized learning support anytime — no waiting for a teacher.
What it does:
Instant explanations on any topic
AI-generated practice quizzes
Step-by-step problem solving
Clean interactive chat interface
Available 24/7 — never offline
Tech Stack:
Python — AI logic and content generation
FastAPI — fast and reliable backend API
Next.js — clean, responsive chat frontend
Claude API — powering the intelligence
Skills:
Python, FastAPI, Next.js, Claude API, Artificial Intelligence, EdTech, Full Stack, Chatbot
Portfolio:
https://my-portfolio-vb6p.vercel.app/
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
Creating immersive digital experiences with smooth website animations ✨
Designed & developed by Usman DevHub Tech & Creative Studio.
We create premium websites with modern UI, interactive animations, and unique visual experiences that help brands stand out. 🚀
Want a website like this for your brand?
DM us and let's discuss your project.
#WebDesign #WebDevelopment #WebsiteAnimation #UIDesign #CreativeStudio #DigitalAgency #UsmanDevHub
Love this, Usman! You drop something amazing every single time.
Receiving feedback is not the same as having permission to publish it.
That distinction shaped ReviewDesk, a customer feedback and testimonial system I designed and built at Noerong.
For a local business, the workflow starts after a completed job: request honest feedback, keep track of the response, and make the next step clear.
Three decisions shaped the experience:
1. Keep the customer journey focused.
A branded page and private request link make it clear where to respond. Scheduled reminders stop after a response.
2. Separate feedback from public proof.
Testimonial consent and administrator approval are distinct steps. Every rating receives the same public-review option, without filtering out unhappy customers.
3. Give the business a useful overview.
The dashboard brings requests, responses, activity, and approval status together. Approved testimonials can appear on a public wall or an embeddable website widget.
I designed and developed the customer flow, dashboard, reminder worker, and widget using Python and FastAPI.
The loop shows the feedback page, business dashboard, and testimonial wall. All customer names, comments, and metrics are fictional demo data. The public demo sends no email and retains no visitor submissions.
The detail I care about most: permission is part of the product, not an afterthought.
Creative work
What if your PC could actually listen, understand, and do the work for you?
I’m building that idea into something real.
Meet AURA — my personal AI voice assistant for Windows.
Instead of building another chatbot that only answers questions, I’m experimenting with an AI agent that can actually interact with my computer and help with everyday work.
So far, AURA can:
• Have live voice conversations
• Convert speech to text and respond with voice
• Open applications like Excel, Power BI, Chrome, and Windows Settings
• Search the web and YouTube through voice
• Perform basic PC and file operations
• Understand requests through Gemini
• Execute actions through a safety-controlled automation layer
• Continue listening after completing a task
But this is only the beginning.
My long-term goal is to make AURA understand my actual workspace — including what’s happening on my screen and inside applications — so I can simply say:
“Open my Excel file, check the sales data, clean the date column, and add a formula for total revenue.”
And let AURA handle the workflow.
I also want it to become useful for my own Data Analytics work — from Excel and Power BI workflows to repetitive desktop tasks, research, and automation.
I’m building AURA with Python, AI, voice technologies, desktop automation, Excel, Power BI, and LLMs, while keeping safety and human control at the core.
It’s still far from the final vision.
But that’s exactly what makes the project interesting.
I’m not just learning how AI agents work.
I’m trying to build one that I can actually use every day.
Building in public. Learning by building. 🚀
#AI #AIAgents #Python #AIAssistant #VoiceAI #DesktopAutomation #DataAnalytics #PowerBI #Excel #Automation #BuildInPublic
The screen-reading step is where I would put the guardrail. Once AURA can read what is in the window, everything on that screen is input - and a page it opened from a voice search can hold a sentence written to be read as an instruction. I spent a while trying to rob my own...