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

Description and use

Seller Assist consolidates AI assistants for inventory, marketing, suppliers, and finance, leveraging open‑weight Gemma models and integrations with TabPFN, SerpApi, and ElevenLabs.

Problem

Running a small business requires handling inventory, marketing, finances, orders, and customer service alone, which can be overwhelming.

Outcome

Seller Assist consolidates multiple business functions into a single AI‑enhanced platform, reducing manual effort and providing real‑time insights for small business owners.

Workflow

• 1. User uploads business data via CSV. 2. Data populates shared workspace. 3. Morgan forecasts inventory and reorder points. 4. Jordan generates listings, SEO tags, and marketing copy. 5. Taylor creates purchase orders and tracks suppliers. 6. Alex calculates budgeting, profit margins, and financial projections. 7. Interactive town and animated characters provide visual feedback and voice narration. 8. Users review dashboards and adjust inputs as needed.

Evidence

Running a small business means doing everything yourself: inventory, marketing, finances, orders, and customer service.

Source

I built Seller Assist, an interactive business workspace with four AI assistants: Morgan, Jordan, Taylor, Alex.

Source

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.

Source

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.

Source

I also incorporated optional integrations for TabPFN forecasting, SerpApi marketplace research, and speech generation.

Source

Users can upload their own business data, which connects to the different workspaces instead of having to enter everything manually.

Source