ListingWriter: I Built a Private AI Property Listing Generator for Nigerian Real Estate Agents

Description and use

ListingWriter lets Nigerian real estate agents quickly generate marketing content for multiple platforms using a locally hosted Gemma 3 model, reducing costs and protecting privacy.

Problem

Real estate agents need to create separate property descriptions for WhatsApp, Instagram and other platforms, which is time‑consuming and costly when using paid AI services.

Outcome

ListingWriter enables Nigerian real estate agents to produce multi‑channel marketing content locally, reducing costs, protecting privacy, and allowing offline use.

Workflow

• 1. Install ListingWriter and required dependencies. 2. Download and configure the Gemma 3 1b model via Ollama. 3. Run the Python application. 4. Input property details and select language. 5. Generate marketing content for all channels locally.
• 6. Review and publish the outputs.
• 7. (Optional) Use the free tier for up to five listings per month or subscribe for unlimited listings.

Evidence

Real estate agents frequently advertise properties across WhatsApp, Instagram, and other platforms. Preparing different descriptions for each channel takes time, and paid AI services can become expensive.

Source

ListingWriter uses Python, Ollama, and Google's open-weight Gemma 3 model.

Source

Agents can generate listings without paying per-request AI API fees.

Source

Local AI processing means property and client information does not need to be sent to an external AI provider.

Source

After downloading and configuring the model, agents can generate content without a continuous internet connection.

Source