The latest articles on DEV Community by Abhishek Kumar (@kabhikumar). https://dev.to/kabhikumar 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%2F4159166%2F7c17d203-720c-44d4-9b22-8b6a20a2473f.png https://dev.to/kabhikumar en Abhishek Kumar Sun, 04 Oct 2026 14:39:13 +0000 https://dev.to/kabhikumar/portfoliopilot-ai-describe-yourself-get-your-portfolio-15kb https://dev.to/kabhikumar/portfoliopilot-ai-describe-yourself-get-your-portfolio-15kb <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><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fbtj9hby9g4bt71z0ngto.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fbtj9hby9g4bt71z0ngto.png" alt="PortfolioPilot AI homepage and landing page" width="800" height="1330"></a><br> I built <strong>PortfolioPilot AI</strong>, an AI-powered portfolio generator designed for a friend who wanted a professional developer portfolio without spending hours writing content, designing sections, and putting everything together manually.</p> <p>The idea is simple: my friend describes themselves in natural language, and PortfolioPilot AI turns that description into a structured, recruiter-ready portfolio.</p> <p>It can generate sections such as:</p> <ul> <li>About / Bio</li> <li>Skills</li> <li>Education</li> <li>Projects</li> <li>Achievements</li> <li>Experience</li> <li>Contact and social links</li> </ul> <p>It also provides a live preview, editable sections, multiple templates, portfolio scoring, and AI-powered improvement suggestions.</p> <h2> Demo </h2> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ftqja43yq5kf1seciacm9.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ftqja43yq5kf1seciacm9.png" alt="PortfolioPilot AI generated portfolio and features" width="800" height="1330"></a><br> The project is currently designed to run locally with Ollama for AI inference.</p> <p>GitHub repository:<br> <a href="https://github.com/abhishek25001011-boop/PortfolioPilot-AI" rel="noopener noreferrer">https://github.com/abhishek25001011-boop/PortfolioPilot-AI</a></p> <p>The repository contains the complete frontend and FastAPI backend needed to run the project locally.</p> <h2> Code </h2> <p>GitHub:<br> <a href="https://github.com/abhishek25001011-boop/PortfolioPilot-AI" rel="noopener noreferrer">https://github.com/abhishek25001011-boop/PortfolioPilot-AI</a></p> <p>The main branch contains the stable version of the project.</p> <h2> How I Built It </h2> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fk8zatf1rljc4q18mpu99.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fk8zatf1rljc4q18mpu99.png" alt="PortfolioPilot AI open-source AI architecture and dark mode" width="800" height="1330"></a><br> PortfolioPilot AI is a full-stack application built with:</p> <ul> <li>React + TypeScript + Vite</li> <li>Python + FastAPI</li> <li>Ollama</li> <li>Qwen Coder, an open-weight AI model</li> <li>LocalStorage for draft persistence</li> </ul> <p>The core flow is:</p> <p>User Prompt → FastAPI → Ollama → Qwen Coder → Structured JSON → Portfolio Preview</p> <p>Instead of using a closed AI API, I used local inference through Ollama. The model generates structur bhaied portfolio information which the frontend then renders into the portfolio UI.</p> <h2> Why Does Open Innovation Matter? </h2> <p>Open innovation made this project possible to run with AI inference locally.</p> <p>Using an open-weight model through Ollama means the core AI generation does not have to depend on a paid closed API. A user can run the model on their own machine and keep their portfolio information local.</p> <p>It also makes the AI layer more flexible: the model can be changed or configured without redesigning the entire application.</p> <p>For a personal tool like this, that gives users more control over their data, model choice, and running costs.</p> <h2> My Agent Session </h2> <p>Not included.</p> <h2> Prize Categories </h2> <p>No partner category selected.</p> devchallenge weekendchallenge hf26challenge