| # CraftPilot: Building a Multi-Agent Craft Business Assistant with a Single Small Model |
|
|
| *How I built a tool for someone I know — a creative introvert who makes beautiful crafts but struggles to sell them.* |
|
|
| ## The Problem |
|
|
| I know someone who crochets, embroiders, paints, and sews the most beautiful things. Friends and family constantly tell her: "You should sell these!" But she never does. Not because the work isn't good enough — it's because the *selling* part is overwhelming. |
|
|
| Writing product descriptions? Agonizing. Picking a fair price? Impossible. Crafting Instagram captions? Exhausting for an introvert. So the crafts pile up, gifted away or tucked into drawers, while she moves on to the next project. |
|
|
| I built CraftPilot to fix that. |
|
|
| ## The Solution |
|
|
| **CraftPilot** is a photo-in, listing-out tool. Upload a photo of your handmade craft, and you get: |
|
|
| - **Catalog metadata** — category, materials, colors, complexity, searchable tags |
| - **Product copy** — a title, short description, full description, and 3 Instagram captions |
| - **Fair pricing** — a price range based on material cost, labor time, and market rates |
| - **Downloadable listing** — export everything as an Etsy/Instagram-ready text file |
| - **Agent traces** — full transparency into what each AI agent did |
|
|
| The key constraint: everything runs on a **single model** (MiniCPM-V 2.6, ~8B parameters) via llama.cpp. No cloud APIs. No subscriptions. No sending your craft photos to OpenAI. |
|
|
| ## How It Works: The Multi-Agent Pipeline |
|
|
| CraftPilot uses a 4-agent pipeline, all powered by the same model: |
|
|
| ``` |
| Photo -> [Vision Agent] -> [Cataloger Agent] -> [Copywriter Agent] |
| -> [Pricer Agent] |
| ``` |
|
|
| 1. **Vision Agent** — Takes the photo and produces a detailed text description of the craft item (materials, colors, techniques, style) |
| 2. **Cataloger Agent** — Reads the description and outputs structured metadata as JSON (category, materials, tags, complexity) |
| 3. **Copywriter Agent** — Takes the catalog data and writes warm, authentic product copy and Instagram captions |
| 4. **Pricer Agent** — Considers materials cost, labor hours, complexity, and market rates to suggest a fair price range |
|
|
| Each agent has a specialized system prompt and outputs structured JSON via constrained generation. The pipeline streams results — you see the vision analysis appear first, then catalog data fills in, then copy and pricing. |
|
|
| ## The Technical Story |
|
|
| ### One Model, Four Agents |
|
|
| MiniCPM-V 2.6 is a multimodal model from OpenBMB that handles both vision (image understanding) and text generation. Running it via llama.cpp means: |
|
|
| - No GPU required (works on CPU) |
| - No API costs |
| - Full privacy — your photos never leave your machine |
|
|
| ### Why Not Just Use ChatGPT? |
|
|
| Fair question. Here's the difference: |
|
|
| - **No account or subscription needed** — privacy matters when selling your own work |
| - **Structured, repeatable outputs** — same format every time, not a wall of text |
| - **Purpose-built workflow** — pricing considers actual material costs and labor hours |
| - **One-click export** — download a ready-to-paste listing for Etsy or Instagram |
|
|
| ### What I Learned About Small Models |
|
|
| A small model is surprisingly capable when you give it: |
| - Clear, focused system prompts (one job per agent) |
| - Structured output constraints (JSON schema) |
| - Pre-computed math (the model can't reliably add, so the pricing template does the arithmetic) |
|
|
| Where it struggles: complex reasoning, nuanced pricing logic, and occasionally inconsistent JSON. Error recovery in the pipeline handles this gracefully — if one agent fails, you still get results from the others. |
|
|
| ## The Stack |
|
|
| - **Model:** MiniCPM-V 2.6 (~8B) via llama-cpp-python |
| - **UI:** Gradio 6.x with custom CSS |
| - **Orchestration:** Python async pipeline with Pydantic models |
| - **Hosting:** Hugging Face Spaces (CPU) |
|
|
| ## What's Next |
|
|
| - Better pricing with real market data integration |
| - Batch processing for multiple items at once |
| - Support for more craft types and regional pricing |
|
|
| ## Try It |
|
|
| CraftPilot is live on Hugging Face Spaces: [Try CraftPilot](https://huggingface.co/spaces/build-small-hackathon/craftpilot) |
|
|
| Built for the Build Small Hackathon 2026 — Backyard AI track. Single model, no cloud APIs, full agent transparency. |
|
|
| --- |
|
|
| *Built with love for someone who deserves to share her craft with the world.* |
|
|
