The latest articles on DEV Community by Kuldeep Dhanora (@kuldeep_dhanora_a763315ea). https://dev.to/kuldeep_dhanora_a763315ea https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4158164%2F27952b78-6c7d-48cd-b921-220a087ccb70.png https://dev.to/kuldeep_dhanora_a763315ea en Kuldeep Dhanora Mon, 05 Oct 2026 08:46:03 +0000 https://dev.to/kuldeep_dhanora_a763315ea/a-patient-practice-partner-for-a-friend-11gc https://dev.to/kuldeep_dhanora_a763315ea/a-patient-practice-partner-for-a-friend-11gc <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-weekend-2026-10-01">Hacktoberfest Weekend Challenge: Build for a Friend</a></em></p> <h2> What I Built </h2> <p>I built a friendly AI-powered language learning web app that helps people practice speaking and writing without being afraid of making mistakes.</p> <p>The app works like a patient practice partner. It:</p> <p>💬 Provides conversational practice<br> ✏️ Gently corrects language mistakes<br> 💡 Gives simple explanations and useful tips<br> 😊 Encourages the learner instead of judging them<br> 🎯 Supports different learning levels<br> 🌍 Supports English, Spanish, and Hindi<br> 📊 Keeps track of practice progress<br> 🤖 AI / Open Innovation</p> <p>The app uses the open-weight openai/gpt-oss-20b model through Hugging Face Inference Providers.</p> <p>I chose an open-weight model because it makes AI experimentation more accessible and gives developers more flexibility when building their own applications.</p> <p>🛠️ How I Built It</p> <p>Technologies used:</p> <p>Python<br> Streamlit<br> Hugging Face<br> openai/gpt-oss-20b<br> Hugging Face Inference Providers</p> <p>The application is deployed as a live Streamlit web app.</p> <h2> Demo </h2> <p><a href="https://patient-language-practice-partner-gje4qeu3l3xp5exymaatyf.streamlit.app/" rel="noopener noreferrer">https://patient-language-practice-partner-gje4qeu3l3xp5exymaatyf.streamlit.app/</a> </p> <h2> Code </h2> <p><a href="https://github.com/kuldeepdhanora40-prog/patient-language-practice-partner.git" rel="noopener noreferrer">https://github.com/kuldeepdhanora40-prog/patient-language-practice-partner.git</a></p> <h2> How I Built It </h2> <p>Technologies used:</p> <p>Python<br> Streamlit<br> Hugging Face<br> openai/gpt-oss-20b<br> Hugging Face Inference Providers</p> <p>The application is deployed as a live Streamlit web app.</p> <h2> Why Does Open Innovation Matter? </h2> <p>Open innovation made it possible for me to experiment with an open-weight AI model and build a useful application without depending entirely on a closed AI API.</p> <p>Using <code>openai/gpt-oss-20b</code> through Hugging Face gave me the flexibility to integrate an open-weight model into my own application and customize the AI's behavior for language-learning practice.</p> <p>For this project, open AI makes experimentation and learning more accessible to developers who want to understand and build with modern AI systems.</p> <h2> My Agent Session </h2> <p>I did not use a DevRelay agent session for this project.</p> <h2> Prize Categories </h2> <ul> <li>AI / Open Innovation</li> <li>Education / Language Learning</li> <li>Open Source</li> </ul> devchallenge weekendchallenge hf26challenge