AI for Architecture

Interactive Maps built with ChatGPT or Claude.

Exploded axonometric diagrams of real sites, made from OpenStreetMap data. Each demo is a small working website: turn layers on and off, change colours, spacing and viewing angle, then export an editable SVG for your boards. Every one was vibe coded from a single prompt, and you can build the same tool for your own site in ChatGPT or Claude.

Live demos free2 demos Build prompts for members
Interactive Maps

Live demos

Exploded map diagrams of real sites, vibe coded in ChatGPT or Claude. Open a demo and use it right here: rotate it, recolour the layers and export the SVG.

Live demos free Prompts for members
Demo 01 Premium
MappingAxonometricSVG Export

London Layer Atlas

Explore a London site through five exploded axonometric layers. Adjust colours, spacing and viewing angles, and export an editable SVG.

Build it yourself in ChatGPT or Claude

Build prompt Members only
Demo 02 Premium
MappingSite AnalysisSVG Export

London Circle Studio

Take apart a 1 km circle of Westminster as five stacked map plates. Toggle and recolour layers, change elevation and rotation, and export an editable SVG.

Build it yourself in ChatGPT or Claude

Build prompt Members only
Download Circle Atlas skill (.zip) Members only

How to use a demo

  1. Click Try Demo. The map opens on this page. Use Open Full Screen ↗ for more room.
  2. Switch the view between Exploded and Site plan.
  3. Turn layers on and off (buildings, transport, water, green space) and click a colour swatch to recolour a layer.
  4. Drag the sliders to change layer spacing, view angle and rotation.
  5. Toggle the base between aerial imagery and the combined vector map, and show or hide the guides and labels.
  6. Export SVG. Each layer comes out as its own group of editable vector paths, ready for Illustrator, Affinity Designer, Rhino or Figma.

What you are looking at

Every plate shows the same piece of the city, at the same scale and in the same position, so the layers line up exactly when they are stacked. The map data is real OpenStreetMap data, downloaded once when the demo was built and saved with the website. Opening a demo or exporting an SVG never calls ChatGPT, Claude or any other AI, and needs no account.

OpenStreetMap is made by volunteers, so a missing building or path in the data does not mean it is missing on the ground. Road widths are drawn as a simple hierarchy, not surveyed widths.

Use your own site

  1. Unlock and copy the build prompt from the demo card above (members).
  2. Find your site centre. In Google Maps, right-click your site and click the coordinates at the top of the menu to copy them (latitude, longitude).
  3. Fill in the brackets in the prompt: site name, city and country, centre coordinates, the size of the study area, the page title and your brand.
  4. Paste it into ChatGPT or Claude, in a mode that can run code and reach the internet, so it can download the real map data. Claude Code works well for this. A plain chat with no tools can still write the code, but you will have to run the data step yourself.
  5. Check the result before you share it: the main river and parks are there, the edges of the study area contain data, the data date is today's date, and the © OpenStreetMap contributors credit is visible.
  6. Publish it. The finished demo is a folder of static files, so it can go on any static host (Vercel, Netlify, GitHub Pages) or the hosting your AI tool offers.

Tips

Keep the area sensible. 1 to 2 km across works well. Dense city centres produce a lot of data, so use a smaller radius there if the page feels slow.

Change one thing at a time. After the first version works, ask for one change per message: a new colour palette, a sixth layer (for example railways or contours), a different title style.

Aerial imagery has its own rules. Satellite and aerial images come from providers such as Esri with their own terms. Check that you are allowed to show and export them in your project, or use the vector base only.

The skill files help. Where a demo includes a downloadable skill, give it to ChatGPT or Claude together with the prompt to get closer to the original look.

Build an open platform

The demos are fixed-site on purpose: the data is downloaded once, so they load instantly and cost almost nothing to host. An open platform lets any visitor choose their own site, which means fetching map data live. That changes what you need:

  • Location search. Visitors type an address and a geocoder turns it into coordinates. Nominatim, the free OpenStreetMap geocoder, allows only light use (about one request per second), so a public tool needs a commercial geocoder or its own instance.
  • Map data on demand. The public Overpass servers are shared and rate-limited, so do not call them from every visitor's browser. Add a small backend that limits the radius, caches each area it has already downloaded and queues requests, or run your own Overpass server or use vector tiles.
  • Processing. Projection, clipping and simplification move to the backend or a Web Worker, with a cap on the number of features, so dense cities do not freeze the page.
  • Aerial imagery. Esri World Imagery in a public app needs an ArcGIS account and API key and must follow its terms. Otherwise offer the vector base only.
  • Cost and abuse. Set a maximum radius, rate-limit each visitor, cache popular places and watch your usage. Hosting a backend and paid APIs can cost money as traffic grows.
  • Still no AI per visitor. ChatGPT or Claude builds the platform. Visitors only use ordinary maps and code, so there is no AI bill per click and no API key in the page.

How to ask for it

Start from a working fixed-site demo, then ask ChatGPT or Claude for the upgrade in plain words, for example: "Turn this into an open tool: add an address search, load OpenStreetMap data for the chosen site through a small server-side API with caching and a 2 km maximum radius, show a loading state and clear errors, and keep all styling, layers and SVG export the same. Do not call any AI model when visitors use it."

Build it in stages: address search first, then live data with caching, then limits and error messages, then deployment. Test with a small town, a dense city centre and a coastline before you share it.

ChatGPT or Claude?

Both can build these demos from the same prompt. What matters more is the mode you use: it needs to run code, download data and save files. Use whichever you already pay for, and switch if one gets stuck.

FAQ

Interactive Maps

Do I need to know how to code?

No. The prompt describes the whole website. You paste it into ChatGPT or Claude, fill in your site and check the result. Knowing how to open a folder and upload it to a host helps when you publish.

Is it free to use the demos?

Yes. The live demos and SVG export are free for everyone. The build prompts and skill downloads are part of the membership.

Can I use the exported SVG in my projects?

Yes, with the © OpenStreetMap contributors credit (ODbL licence). Aerial imagery follows its provider's terms, so check those before you publish it.

Does it work for any city?

Yes, anywhere OpenStreetMap has data. The detail varies by place, and very dense areas may need a smaller study area.

Will the website call AI every time someone uses it?

No. AI is only used once, to build the site. The finished demo is ordinary HTML, CSS and JavaScript with the map data saved inside it.

Get every prompt in the library

240 tested prompts, 227 worked examples and 466 before/after images for Nano Banana and ChatGPT, plus the 291-page bilingual PDF guide.

Get the full library

Sign in to AI for Architecture

Sign in to subscribe and unlock every prompt on any device.

or

Esc
Get new prompts & AI tool news weeklyOne email a week. Unsubscribe anytime.