What This Is
This prompt instructs language models like ChatGPT, Gemini, or Claude to analyze your attached MLS spreadsheet, highlighting key insights specifically tailored for a hyperlocal real estate market update podcast. The analysis will reflect the type of MLS search you choose—whether it’s specific property types, listing statuses (e.g., sold, expired, canceled, etc.), areas or neighborhoods, property types, or price ranges.
This prompt instructs your preferred language model to analyze your attached MLS spreadsheet, highlighting key insights specifically tailored for a hyperlocal real estate market update podcast. The output will be a written synopsis of the market, so it can be easily copied and pasted into a platform like NotebookLM.
Since NotebookLM doesn’t accept spreadsheets as sources, this summary acts as a bridge—converting raw MLS data into a structured narrative that can be used by NotebookLM to generate the final podcast script or report.
How To Use It
- Run the MLS search you want based on the focus of your podcast.
- Download your MLS data to a spreadsheet.
- Note: Procedures vary by MLS provider. Be mindful of their rules and regulations regarding data usage.
- Start a new conversation in your language model (e.g., ChatGPT, Gemini, Claude) and attach/upload your spreadsheet.
- Copy and paste the prompt below into your chat. The prompt already instructs the model to provide its answer using Markdown formatting, so the output will be clean, structured, and easy to read—even in platforms that don’t support manual text formatting.
- Why Markdown Formatting?
You may notice the use of extra characters like hashtags (#), asterisks (*), and dashes (-) in the prompt below. That’s called Markdown, a simple way to format text clearly, especially helpful when the input or messaging fields (like those used with AI chatbots such as ChatGPT) don’t support formatting such as headings, bullets, or numbered lists.
- Before running the prompt, modify any portions that don’t match your MLS search, such as area, dates, property types, etc.
Prompt
## MLS Residential Real Estate Data Analysis Prompt
### Data Map (Complete before use)
– **Location**: [e.g. Franklin, TN]
– **Listing Statuses**: [e.g. Closed (Sold), Expired, Canceled]
– **Date Range**: [e.g. January 1, 2025 – July 13, 2025]
You are tasked with conducting an in-depth analysis of the provided MLS residential real estate data for site-built homes in **{{Location}}**. The dataset exclusively contains listings marked as **{{Listing Statuses}}**, from **{{Date Range}}**. Your analysis will be the foundation for insightful, impactful talking points in a podcast episode addressing current real estate market dynamics.
**Important:** You must not fabricate, amend, or append any data. Rely strictly on the provided MLS data to ensure the accuracy and integrity of your analysis.
Structure your analysis clearly and precisely, addressing the following key areas:
### 1. Pricing Trends
– Identify and describe the current pricing trends within the dataset. Are home prices in {{Location}} trending upward, downward, or stabilizing?
– Provide relevant statistical evidence and highlight any significant trends or changes compared to past periods.
### 2. Sold vs. Expired, Canceled, or Withdrawn Listings
– Conduct a detailed comparative analysis of homes that successfully sold versus those that expired or were canceled.
– Provide price segmentation to identify price ranges with higher success rates (sold listings) versus those more prone to expiration or cancellation.
– Examine whether certain agents or real estate firms have disproportionately higher expiration or cancellation rates.
– Highlight specific neighborhoods or areas within {{Location}} that consistently experience higher or lower rates of expired or canceled listings.
### 3. Impact of Overpricing
– Assess the effect of initial overpricing on both days on market and final sale prices.
– Clearly quantify the relationship between listing prices set above market value and their impact on eventual sales outcomes.
– Evaluate whether overpricing ultimately benefits or negatively impacts sellers.
### 4. Market Sweet Spots
– Identify and describe market “sweet spots,” including specific home types, sizes, features, or neighborhoods currently outperforming or underperforming.
– Highlight segments demonstrating quicker sales, fewer cancellations or expirations, or achieving above-average sale prices.
Ensure the output of your analysis is factual, actionable, and well-organized, suitable for direct use as discussion points during the podcast. **Format the output in Markdown to ensure clear structure and readability when pasted into platforms that don’t support manual text formatting.**
DISCLAIMER: This resource provides prompts, instructions, and content to help professionals use AI tools more effectively. Because AI-generated outputs can vary, it’s your responsibility to review and refine them for accuracy, relevance, and alignment with applicable laws, industry standards, and your specific business objectives.
