For the complete documentation index, see llms.txt. This page is also available as Markdown.

Prompting tips

Write clearer prompts for Felt AI. Get examples for the AI assistant, extensions, custom HTML popups, and SQL queries.

Give Felt AI specific names and values, whether you're using the AI assistant, building an extension or popup, or writing SQL. For example:

Filter the "permits" layer to show only records where permit_type is "residential" and status is "pending".

A less specific prompt leaves Felt AI to guess which layer and attributes you mean:

Show me the pending residential permits.

Where you use Felt AI

Felt AI works in two places, and prompts work a little differently in each.

  • The AI assistant: the Felt AI panel on a map. It answers questions and changes the map for you, such as adding data, running analysis, and styling layers. See Prompts in the AI assistant.

  • The Felt AI editors: a Felt AI tab inside the Extension editor, the custom HTML popup editor, and the SQL query editor. There, Felt AI drafts code that you read, edit, and run or save yourself. See Prompts in the Felt AI editors.

Tips for every prompt

  • Say what to do with missing data, such as "If assessed_value is null, show Not available."

  • Give an example of the format you want, such as "Format dates as March 15, 2025, and currency as $1,250,000."

  • Build in small steps so you can check and fix each result before moving on.

  • When a result isn't right, ask for changes in the same conversation instead of starting over.

Prompts in the AI assistant

Give Felt AI your goal and the layers and place it's about, and let it choose the data, analysis, and styling that fit:

I'm reviewing our store network in Ohio. Add the county boundaries for Ohio, color the stores layer by region, and add a bar chart of region and a filter for status.

  • Name the layer and the attribute to use: "Color the stores layer by region", not "Color the stores". To pick the exact layer or source, enter @ in the prompt box.

  • Name the place when you ask for data, such as "Add census tracts for Travis County, Texas." Without a place, Felt AI may add data for the wrong area.

  • Ask for the result you want. "Add the county boundaries for Ohio" adds a layer. "How do I add county boundaries?" gets instructions.

  • Select a feature, an annotation, or a polygon you drew, and refer to it as "the selected area".

  • For a chart or filter, name the layer, the component, and the attribute: "On the permits layer, add a bar chart of permit_type and a filter for status."

  • Refine the result as you'd direct a colleague: "Make the high-risk zones more prominent and mute everything else."

  • Ask Felt AI to explain what it did: "Which data source did that layer come from?"

  • Click New chat when you switch to an unrelated task. A focused conversation gets better results.

Prompts to start with

Replace the layer, attribute, and place names with your own.

To
Enter

Get to know a layer

What's in the stores layer? List the columns, give me the key numbers, and suggest three ways to map it.

Style a layer by an attribute

Color the stores layer by region and label each store with its name.

Show only some features

Show only the features in the permits layer where status is pending.

Add a chart and a filter

On the stores layer, add a bar chart of region and a filter for status.

Find rows that didn't get a location

Which rows in the customers layer didn't get a location on the map, and why?

Map a list of places

Put these places on the map: followed by one address or place per line, each with its city and state or country

Add boundaries for an area

Add the boundary of Lyon and zoom the map to it. or, in the US, Add ZIP codes and census tracts for Travis County, Texas.

Add US public data for an area

Show the FEMA flood zones in Houston. or Add power lines and substations near Denver.

Add terrain

Add hillshade and contour lines for the Lake District.

To use your own file, upload it first, then ask Felt AI about the layer.

Learn as you go

Ask Felt AI to teach you Felt while you work:

  • "How do I upload a spreadsheet of addresses?"

  • "How do I change these colors?"

  • "Explain what you just did"

  • "What does this layer show?"

  • "Explain the process before you run it"

  • "Ask me questions as you go"

Prompts in the Felt AI editors

The Felt AI editors draft code that you can read, edit, and run.

Extensions

In the Felt AI tab of the Extension editor, Felt AI drafts JavaScript SDK code for an extension, an interactive tool on your map. Describe what starts the extension, which layers it uses, what it shows, and how to clear results. If the extension needs to do several things, number the requirements:

Create an interactive tool where I can click any school to find nearby parcels. When I click a school:

  1. Draw a 500-meter buffer around it.

  2. Filter the parcels within that radius.

  3. Show a panel with the school name, the count of nearby parcels, and each parcel's zoning type and assessed value.

  4. Clear previous results when I click a different school.

To get advice instead of code, add "don't write code" to your prompt. To fix a problem, test each part and ask for a specific change, such as "The count isn't updating when I change the filter."

Extension editor with the Felt AI tab open, suggested prompts, a typed prompt to zoom to the highest-income county, and the map preview.

Custom HTML popups

For custom HTML popups, Felt AI drafts the HTML, CSS, and JavaScript. Name the attributes to show and how to format each one. Specify any colors, icons, links, or images:

Create a popup showing the address as a bold heading, the price as currency, bedrooms and bathrooms as "3 bd | 2 ba", and a "View listing" link that uses the listing_url attribute.

Preview the popup in the desktop and mobile layouts before you save.

SQL queries

For SQL queries on a database source, Felt AI writes SQL you can inspect, edit, and run. The results become a layer. Name the tables to query, the filters to apply, and the attributes to return. Describe the spatial relationship, such as intersecting an area or being within a distance:

Find all fire stations within 2 miles of areas where response times exceeded 10 minutes last year. Join with the incidents table and show the count of slow responses per station.

If you're not sure what's in your database, ask first: "What tables do I have related to emergency response?" If a query is slow or returns too much data, ask Felt AI to optimize it or add a limit.

Last updated

Was this helpful?