Connect your data to your favorite AI
FetchBrick datasets are designed to work seamlessly with modern AI assistants. Whether you need a quick market overview or deep competitive analysis, here is how to get started in under two minutes.
Claude
Complex analysis & large files
ChatGPT
Creative brainstorming & charts
Gemini
Real-time web research
Method 1: No downloads required.
Modern AIs like Claude and ChatGPT can now read URLs directly. Just copy the AI Context Link from any retailer page and paste it into your chat. The AI will fetch the structured data and understand the schema automatically.
This is the fastest way to get started. Each retailer page on FetchBrick includes a dedicated AI Context endpoint that serves a machine-readable summary of the retailer's location data, including store counts by province, data field definitions, and sample records. The AI can then answer questions about coverage, density, and distribution without you needing to download or upload anything.
"Claude, analyze the retailer distribution at this link: fetchbrick.com/..."
Based on the context provided, Delhaize has a significantly higher density in Brussels (142 stores) compared to Antwerp (89 stores)...
delhaize_locations.csv
1.2 MB • Ready to use
Drag & Drop into ChatGPT
Method 2: Deep Data Analysis
For complex mapping, full territory analysis, or when you need to work with the complete dataset, download the CSV file and upload it directly to your AI assistant. This method gives you access to every single data point, including precise geocoding for all stores.
CSV uploads are particularly powerful when you need the AI to perform calculations across the full dataset, such as computing average distances between stores, identifying clustering patterns, or comparing coverage across multiple chains simultaneously. Claude and ChatGPT can both handle files with thousands of rows comfortably.
- Plot hundreds of points on a map
- Create distance-based calculations
- Cross-reference multiple retailer files
- Generate custom visualizations and charts
Choosing the right AI model
Each AI assistant has different strengths when working with location data. Here is how they compare for typical retail analysis tasks.
Claude
Best for working with large files and complex multi-step analysis. Claude's 200K context window means it can process entire retailer datasets in a single conversation without truncation.
- Handles full CSV uploads (thousands of rows)
- Reads AI Context URLs directly
- Strong at structured data reasoning
ChatGPT
Excels at creating visual outputs. ChatGPT's Code Interpreter can generate maps, charts, and data visualizations directly from your CSV file, making it ideal for presentation-ready analysis.
- Generates maps and scatter plots
- Runs Python code on your data
- Exports charts as downloadable images
Gemini
Strongest for combining your dataset with live web information. Gemini can cross-reference your FetchBrick data with Google Maps, recent news about store openings, and public demographic data.
- Cross-references with live Google data
- Integrates Google Sheets and Docs
- Adds real-time context to analysis
Best practices for AI-powered location analysis
Follow these tips to get the most accurate and useful results from your AI assistant when working with FetchBrick data.
1. Reference the data source
Always mention that your data comes from FetchBrick and include a link to the documentation. This helps the AI understand the schema, field definitions, and data freshness. Start your prompt with:
2. Be specific about geography
Belgian geography can be confusing for AI models not familiar with the country's structure. Specify whether you mean a province (Antwerp, East Flanders), a city (Antwerp, Ghent), or a region (Flanders, Wallonia, Brussels-Capital). This prevents the AI from conflating the city of Antwerp with the province of Antwerp, which have very different geographic scopes.
3. Use coordinates for spatial queries
When asking about proximity, drive-time, or coverage area questions, make sure you are using the Pro or Enterprise tier dataset that includes latitude and longitude coordinates. The free directory includes name, city, and postal code, but without coordinates the AI cannot calculate distances or create spatial visualizations.
4. Compare across chains
The most valuable insights come from comparing multiple retailers. Upload two or three CSV files from competing chains and ask the AI to identify where one brand is dominant and where the other has opportunities. For example, compare Delhaize vs. Carrefour in Brussels, or Aldi vs. Lidl across Flanders.
Prompts to try
Copy and paste these questions to get instant insights from your data.
Market Gap Analysis
"I am using data from fetchbrick.com (documentation at fetchbrick.com/llm.md). I'm attaching a list of all Colruyt stores in Antwerp. Can you identify neighborhoods that are currently underserved or far from any existing store?"
Competitor Comparison
"I am using data from fetchbrick.com (documentation at fetchbrick.com/llm.md). Based on these two files (Delhaize and Carrefour), which brand has a stronger presence in the city center of Brussels vs. the outskirts?"
Expansion Planning
"I am using data from fetchbrick.com. Here is the full list of Aldi stores in Belgium. Can you identify the 5 provinces where Aldi has the weakest coverage relative to population density?"
Drive-Time Analysis
"I am using data from fetchbrick.com. Using this Colruyt dataset, estimate how many people in East Flanders live more than 10 km from the nearest Colruyt. Which cities would benefit most from a new store?"
Start analyzing today.
Get a free 10% sample of any dataset and see what an AI can do with it.