Workflow

A better map starts before the prompt.

Prompt cartography is a practical workflow for directing, critiquing, and revising AI-assisted maps without surrendering cartographic judgment.

Try the 10-minute workflow Explore the pipeline Visit WebMapGPT

Casual request Make a flood risk map.

Prompt cartography adds Audience, data limits, visual hierarchy, uncertainty, critique, revision.

Defensible map brief A map someone can use, question, revise, and cite.

Quick start

The whole method in three moves.

Use this when you want the workflow to feel like a friendly studio practice instead of a checklist with a clipboard.

Frame

Clarify audience, purpose, data readiness, and cartographic strategy before asking a model to draw anything.

Start with intent

Make

Turn the design problem into a prompt brief, generate a draft, critique the result, and write targeted revision prompts.

Open the making loop

Prove

Check accessibility, ethics, uncertainty, publication context, and reproducibility before calling the map finished.

Finish responsibly

Full pipeline

Click a stage. See what it does.

Each stage makes one kind of cartographic judgment visible, reusable, and easier to critique.

Frame Chapter 1

Intent & audience

Define who the map serves and what decision, memory, or conversation it should support.

What you do

Interview the map idea: audience, setting, decision, emotional tone, device, and what the user should remember.

Why it matters

LLMs default to generic map-shaped output unless you provide purpose, audience, and constraints.

Try this prompt

Act as a cartographic project interviewer. Ask me five questions that clarify the map audience, task, data, risk, and final deliverable.

Skeptic check

If you skip this, the model may optimize for a plausible-looking map instead of a useful one.

Open related lab Browse prompts

Before / after

What changes when the workflow shows up?

The point is not a longer prompt. The point is a map brief with enough judgment in it to be tested.

Before

Make a pretty population map.

The model has to invent the audience, purpose, classification, palette, legend behavior, source note, and standard of success.

After

Create a county population-density map for regional planners comparing settlement patterns.

Use a sequential color-safe palette, explain class breaks, prioritize regional comparison, cite the data source, and include one uncertainty note about county-level aggregation.

Choose your path

Where should you go next?

Different visitors need different proof. Start with the door that matches your curiosity.

I'm newLearn by doing

Start with beginner labs that turn casual map ideas into critique-ready prompt briefs.

I'm skepticalSee AI web mapping in the wild

Visit WebMapGPT for a more direct encounter with prompt-driven web map generation.

I'm teaching thisUse the classroom kit

Find chapter alignment, rubrics, assignments, discussion prompts, and adoption support.

I'm ready to use itBrowse reusable prompts

Copy prompts, schemas, and critique agents organized by workflow stage.

The full method

Want the whole Prompt Cartography stack?

The site gives you working pieces of the method. The book teaches the complete workflow: why each stage exists, how to adapt it, and how to avoid the easy failure modes of AI-generated cartography.

Get the book