Seller Assist 🌸: I Built an AI Team to Help Run Your Side Hustle

jhusk003 — Mon, 19 Oct 2026 06:58:39 +0000

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

What I Built

Running a small business means doing everything yourself: inventory, marketing, finances, orders, and customer service. I wanted to make that a little easier.
So I built Seller Assist, an interactive business workspace with four AI assistants:
•📦 Morgan: Inventory and forecasting.
•🎨 Jordan: Listings, SEO, and marketing.
•📋 Taylor: Suppliers, purchase orders, and operations.
•💰 Alex: Budgeting, profit, and financial planning.
Each has its own personality and workspace, but they connect to shared business information.
I also built an explorable illustrated town, interactive dashboard, CSV uploads, business calculators, and animated talking characters.
I built Seller Assist with independent sellers, Etsy and Shopify shop owners, and people starting their first side hustle in mind. My idea is to eventually offer an affordable subscription for advanced AI features while keeping the basic business tools accessible. I wanted to create something that makes managing a business feel less overwhelming, especially when you're doing everything on your own.

Demo

Try Seller Assist: https://seller-assist-ai-749368.onrender.com/

Video walkthrough:

Code

GitHub: https://github.com/jhusk003/multi-workflow-ai

jhusk003 / multi-workflow-ai

multi-workflow-ai

View on GitHub

How I Built It

I built Seller Assist using Python and Streamlit for the main application, along with HTML, CSS, JavaScript, and WebGL for the interactive town, dashboards, and animated characters.
The AI system is built around Google's open-weight Gemma models, with separate configurations for each of my four assistants so they have different specialties rather than giving the same generic responses. I also implemented a Gemini fallback to help with model availability issues.
For the business features, I used Python to handle calculations like profit margins, inventory levels, sales velocity, and reorder quantities. I also incorporated optional integrations for TabPFN forecasting, SerpApi marketplace research, and speech generation. Users can upload their own business data, which connects to the different workspaces instead of having to enter everything manually.
One of the biggest challenges was getting all the features to work together, especially making the characters speak, blink, and move their mouths naturally without distorting their faces. I also had to work through API connection errors, deployment issues, and merging different versions of my application.
I also made sure the numerical business calculations were handled separately in Python rather than relying entirely on AI-generated answers, so things like reorder quantities and profit estimates could be calculated consistently.
There was definitely a lot of trial and error involved, but I learned quite a bit about connecting AI models to practical tools and turning separate features into one functioning application!

Why Does Open Innovation Matter?

Open innovation gave me the freedom to experiment, customize, and build Seller Assist without being limited to one AI provider or having to create everything from scratch. Using Gemma's open-weight models also gives me more control over how I develop my AI assistants, with the possibility of exploring self-hosting and other deployment options in the future.
A big part of building this project was trial and error. I was constantly testing different tools, improving features, and figuring out how to connect everything into one application. Having access to open technologies made that process much more flexible than relying entirely on a closed API.
I think that's what makes open innovation important. It gives individual developers the opportunity to build things that might otherwise require a much larger team or budget. With Seller Assist, I wanted to use that accessibility to create something that could eventually help other people grow their own small businesses, too.

Prize Categories

Best Use of Render — Hosting my interactive Seller Assist application.
Best Use of Gemma — Using open-weight AI to power my four specialized business assistants.
Best Use of TabPFN — Integrating predictive inventory forecasting using historical sales data.
Best Use of ElevenLabs — Giving my AI characters generated voices.
Best Use of SerpApi — Incorporating live competitor and marketplace research.

Team Members: Just me! 😊

This was my first version of Seller Assist, and there's still more I want to improve, but I'm happy with how much I was able to build for this challenge. Thanks for checking it out!

Fresh Air Writing Challenge Submission

jhusk003 — Mon, 12 Oct 2026 17:35:16 +0000

This is a submission for the MLH x DEV Writing Challenge

What I Built

I built Fresh Air, an AI-powered application with a simple idea behind it: Get out your feelings and get outside.

I wanted to explore how AI could encourage people to do things away from their screens instead of giving them another reason to stay online. Fresh Air generates personalized outdoor missions, suggests alternative activities, translates instructions, and lets users record completed missions in a journal. The goal is to make it easier to take a break, try something new, and reconnect with the world around you.

I built the application using Python and Streamlit, with Ollama powering mission generation, MongoDB Atlas supporting persistent journal data, SerpApi supporting information retrieval, and ElevenLabs providing voice narration.

Demo

Live application: [https://fresh-air.onrender.com]
Source code: Fresh Air on GitHub
Demo video: [https://youtu.be/foO0ND69uxw?si=tRX-9L7wzlGCmzzH]

The demo walks through the main features, including generating missions, exploring alternatives, translating instructions, and tracking completed activities.

Partner Technologies

I used several technologies to bring Fresh Air together. MongoDB Atlas supports persistent journal data, ElevenLabs provides AI-generated voice narration, and SerpApi supports information retrieval. Ollama runs a language model that helps generate mission ideas, while Python and Streamlit power the application's logic and interface.

Getting these technologies to work together was one of the biggest challenges. I had to troubleshoot configurations, test integrations, and adjust features to make the experience as straightforward as possible. This taught me that building an AI application involves more than getting a model to generate text; the different components need to work together to solve a real problem.

Hackathon Experience

Building Fresh Air gave me the opportunity to take an idea I cared about and turn it into something people could interact with. I wanted to explore a practical use of AI that encourages people to spend less time online and more time engaging with their surroundings.

The process pushed me to think about why each feature mattered, how different technologies could support the same goal, and how to keep going when things didn't work as expected. My biggest takeaway is that AI doesn't always need to keep people engaged with technology. Sometimes, it can help them step away from it.

Fresh Air is my reminder that sometimes we need to get out of our heads, get outside, and reconnect with the world beyond the screen.

DEV Community: jhusk003

Seller Assist 🌸: I Built an AI Team to Help Run Your Side Hustle

What I Built

Demo

Code

jhusk003 / multi-workflow-ai

multi-workflow-ai

How I Built It

Why Does Open Innovation Matter?

Prize Categories

Fresh Air Writing Challenge Submission

What I Built

Demo

Partner Technologies

Hackathon Experience