The AI On-Ramp to a 5 minute Wardley Map

I don't create Wardley Maps often, but I had an idea today I wanted to play with, and the results were surprising enough to share. I've been trying to play with ChatGPT for creating Value Stream Maps and although the results have been surprisingly good, I got curious about what's possible on something more standardized. Here's what it looks like to build a Wardley Map with ChatGPT.

Me: Do you know anything about Wardley Maps?

Yes, I'm familiar with Wardley Maps. Wardley Maps are a strategic tool used in business to visualize and understand the competitive landscape, identify opportunities for innovation, and make better decisions. They were developed by Simon Wardley, a British researcher and business consultant, in the early 2010s.

A Wardley Map consists of a two-dimensional grid, with the x-axis representing the evolution of components (from genesis, to custom built, to product/rental, to commodity/utility) and the y-axis representing the value chain (from user needs at the top to more invisible, underlying components at the bottom). By mapping out the various components, dependencies, and their current stage of evolution, a company can better understand the competitive landscape and make more informed decisions about where to invest, what to build or buy, and when to outsource.

To create a Wardley Map, follow these general steps:

Identify user needs: Determine the primary needs of the end-users that your organization is trying to address.

Break down the value chain: Decompose the problem into smaller components that are required to fulfill the user needs. This helps create a better understanding of the dependencies between components.

Determine the evolution stage of each component: For each component, assess its current stage of development along the x-axis (genesis, custom built, product/rental, or commodity/utility).

Plot the components on the map: Place each component on the map according to its position in the value chain (y-axis) and its stage of evolution (x-axis).

Analyze the map: Identify areas where your organization can innovate, improve efficiency, or outsource to gain a competitive advantage.

Wardley Maps can be a valuable tool for organizations of all sizes and across various industries. They help teams better understand their current situation and make more informed decisions about resource allocation, product development, and strategic direction.

Great. We're going to skip all that and just get playing ??

?? Don't do this if you haven't done discovery, mapped your value chain or if you're mapping with a group. This is great for playing around and getting a feel for what's possible with an AI mapping assistant.

?? Warning: This is a dumb map for demonstration purposes ??

Let's dig in.

To start, I went to onlinewardleymaps.com and started with the Example Map.

I copied all the config from the left and jumped back to ChatGPT:

Me: If I give you the following wardley map data, containing X and Y coordinates for each axis, can you help me change it?

title Tea Shop
anchor Business [0.95, 0.63]
anchor Public [0.95, 0.78]
component Cup of Tea [0.79, 0.61] label [19, -4]
component Cup [0.73, 0.78]
component Tea [0.63, 0.81]
component Hot Water [0.52, 0.80]
component Water [0.38, 0.82]
component Kettle [0.43, 0.35] label [-57, 4]
evolve Kettle 0.62 label [16, 7]
component Power [0.1, 0.7] label [-27, 20]
evolve Power 0.89 label [-12, 21]
Business->Cup of Tea
Public->Cup of Tea
Cup of Tea->Cup
Cup of Tea->Tea
Cup of Tea->Hot Water
Hot Water->Water
Hot Water->Kettle 
Kettle->Powerp        

Of course, I can help you with that. Please let me know the changes you'd like to make to the Wardley Map data, and I will modify the provided data accordingly.

Me: I'd like to convert the subject matter from making tea to building software, and repurpose items like the kettle to be an internal development platform. Can you help me adapt the content to that context?

Certainly! Here's a modified version of the Wardley Map data with the subject matter changed to building software and the components adapted accordingly:

title Software Development 
anchor Business [0.95, 0.63] 
anchor Users [0.95, 0.78] 
component Software Solution [0.79, 0.61] label [19, -4] 
component User Interface [0.73, 0.78] 
component Backend [0.63, 0.81] 
component APIs [0.52, 0.80] 
component Data Storage [0.38, 0.82] 
component Internal Development Platform [0.43, 0.35] label [-57, 4] 
evolve Internal Development Platform 0.62 label [16, 7] 
component Infrastructure [0.1, 0.7] label [-27, 20] 
evolve Infrastructure 0.89 label [-12, 21] 
Business->Software Solution 
Users->Software Solution 
Software Solution->User Interface 
Software Solution->Backend 
Backend->APIs 
APIs->Data Storage 
APIs->Internal Development Platform 
Internal Development Platform->Infrastructure         

Me: Remove Software Solution and shift User Interface into Custom Built on the X axis

Progress, but ChatGPT doesn't actually understand our axes in relation to the coordinates yet (we could set this context from the start next time). Let's fix it.

Me: Rename the map to Platform Evolution and Shift User Interface moved down on the Y axis, but I need it moved 80% left on the X axis. User Interface moved on the wrong axis, can you reverse the coordinates? Business is also still connected to User Interface, can you remove it? Move Users to be vertically aligned with User Interface and Business to be aligned with Backend.

In this updated map:

• The title has been changed to "Platform Evolution."
• The "User Interface" component has been moved 80% left on the X axis, coordinates have been reversed, making its new position (0.09, 0.78).

One last tweak:

Me: Connect Data Storage to Infrastructure

Here's where we end up!

Pretty impressive for a few minutes of playing around. ??