DoView Boards
“Sometimes elegance
and simplicity define use”
Plan anything with a DoView Board
Quick Overview
You can build a DoView Board about anything, for instance, a family holiday, moving house, a company's strategy, self-development, building a customer service AI agent, creating world peace. . . let your imagination run wild!
They are drill-down visual planning and coordination boards based on This→Then causal logic. You can use them in many formats, for instance as an interactive webpage model, PowerPoint, PDF etc. They help you plan by structuring your thinking around the This→Then logic of the steps that need to happen as you collect information, plan, act and move onto the next steps you need to take.
In addition, they have the potential to provide a GUI-type visual interface, making it easier for humans to interact with AI systems using a visual rather than a text-based approach, as we use at the moment.
This page gives examples of DoView Boards and several free AI prompts for quickly building them. The first is a Claude prompt for building an interactive webpage DoView (HTML) that you can put information into, chat with, and amend by using Claude chat built into the board. You can also open this in any browser and add information to it. Second, there is a ChatGPT 5.2 prompt that lets you build a DoView Board in Powerpoint. Third, if you want, you can download our award-winning DoView legacy app to and draw DoViews without using AI.
Lastly, there is information for developers who are free to build DoView Boards into any application, platform or system (just with acknowledgement) (see Github). They may wish to extend the use of DoView Boards in a range of ways including the possibility of them being used as interfaces for interacting with AI systems.
Please note that the Claude prompt used here creates a free prototype DoView Board, use at your own risk. See the Disclaimer at the bottom of any DoView Board.
DoView Boards
A DoView Board is simply a This-Then diagram with a set of boxes on the left that need to be done first, to achieve high-level outcome boxes on the right. They can be used to plan anything from a two-day holiday to an entire country’s economic strategy. This works because the common starting point in any planning is identifying the ‘This-Then’ steps that need to be done.
A simple DoView Board of a cycling trip
Below is a static image of a DoView Board created on-the-fly by Claude using the DoView Board Prompt. Claude was given the prompt and then told to ‘create a DoView Board for a cycling trip to the Wairarapa for five adults’. It came up with all the detail in this DoView Board itself. As shown in the subsequent diagram you can use an interactive DoView Board rather than having to have a long-winded text-based discussion with Claude about the trip
An interactive DoView Board of a cycling trip
When using a DoView Board in within Claude you interact with it. Try clicking on a box on the left in the board below. You can enter into it information you want Claude to know about that box. When Claude gives you responses (e.g. where to stay, you put can put that under that box). You can also ask Claude questions about the box (this option does not work in the DoView Board below because you are not using it in Claude). And you can put in your own notes for yourself about the particular box.
Notice how when, for instance, in the Info for AI option, you say ‘completed’, the traffic light on the box will turn green, and if you do this for all of the boxes with orange traffic lights, Claude will then turn orange more of the boxes for you to have input into. So Claude understands the dependencies in the DoView Board.
At any time, you can ask Claude to output the contents of the DoView Board in any format you like (e.g. as an itinerary, a list of gear, etc.) as you normally would when having a long text-based chat with Claude about planning a trip.
A more complex DoView Board: Building a house
DoView Boards are scalable so that you can use them to plan for anything. Here is a DoView Board for everything you need to do to build a house.
A more complex DoView Board: Developing a Customer Service AI Agent
The DoView Board below shows how a DoView Board could be used to plan for building a Customer Service AI Agent.
For developers wanting to push the DoView Board concept further
As noted above, the use of DoView Boards as an intent GUI for interacting with AI systems is a recent development. We can see them as a tool for intent engineering as working with AI moves up the stack from prompt engineering to context engineering, and now to intent engineering. (See Nate Jones on intent engineering). However, the DoView Board concept is not new, it has a fully established theoretical foundation in outcomes theory. The DoView Board approach comes out of strategy psychology. It conceptualilzes any action in the world as always being undertaken by an outcomes system. Such systems can be human, human/AI or A| systems. Outcomes systems specify outcomes, prioritize them, align actions to them, delegate actions, measure their success and use feedback to improve execution.
Every outcomes system has beneath it an implicit or explicit ‘This-Then’ model specifying its strategy space. DoView Boards are a standardized way of visualizing this any outcomes systems ‘This-Then’ logic.
From a strategy psychology point of view, the boards reduce the cognitive load associated with planning and implementation. They do this by getting the mental ‘This-Then’ logic model out of people's heads and into an external shared thinking tool used for group decision-making.
DoView diagrams have been used in thousands of instances to build human organizational ‘This-Then’ models. And the now legacy DoView app for drawing DoView diagrams won Gartner Cool Vendor recognition.
There are multiple ways in which the concept can now be transferred to clarify and implement intent with AI systems.
Optimizing the DoView Board user experience
On-the-fly building of DoView Boards has only become widely doable because of Claude’s interactive diagram feature. However, this feature in Claude (wonderful though it is) is not fully optimized for using a DoView Board as the central artifact that you use to interact with AI. This is because when you ‘Ask AI’ under a box within the DoView Board, Claude returns the answer down the page and it scrolls the user away from the DoView Board, so the user has to scroll back up to it. Also, Claude does not fully update the DoView Board until you type DoView, and it takes some time for it to redraw the board.
At the moment in Claude, if you use the Artifact window, the DoView Board will not interact with the Claude chat in the way that it does when the board is an inline interactive diagram within a Claude chat. You can mock up how a better DoView Board interface would work. Just put the HTML for the DoView Board created by Claude into Open AI’s Atlas browser. Then open up the chat window on the right-hand side of the DoView Board in the browser window. You need to instruct ChatGPT to look for changes in the Your Notes field, which are questions, and then ChatGPT will return a response in the right-hand window. In contrast to what happens with Claude, this means you can still see the DoView Board all the time while interacting with the AI. This mock up in Atlas does not have the full functionality of using the interactive diagram in Claude, it merely demos a better user interface for using a DoView Board as an intent GUI to interact with an AI system.
Using a DoView Board to structure code development
In theory, DoView Boards could be further developed to control code development with different modules being build and tested under different boxes in the DoView Board if the right user interface was built.
Using a DoView Board to control AI agents
DoView diagrams were developed in order to manage and control human agent(s). There is no reason, in theory why they could not be wired up to control AI agents. DoView Board’s drill-down structure makes them scalable. You can just develop subpages with more detail to inform and control agent behavior at a more detailed level.
Could DoView Boards be used by AI agent swarms to plan, coordinate and implement
At the moment, DoView Boards have been optimized for humans. For instance, they are always broken up into subpages which are an optimal size for humans to easily parse and share on standard sizes screens. However, any DoView Board could, in theory, have an accompanying version which is optimized for AI. If you look at the way in which Claude is using the existing DoView Board Prompt, it is building into the board some logic about This-Then dependencies. How much of such logic needs to be built into a standard for an AI-optimized DoView Board would need to be worked out. However, DoView Boards have been used successfully to coordinate, manage and control human organizations so there is no theoretical reason why they might not be of assistance to AI agents trying to coordinate.
Using DoView Boards for as part of the DoView Planning methodology
DoView Boards are used as the central visualized source of strategic truth within DoView Planning. From the point of view of outcomes theory, AI agents working within outcomes systems face exactly the same issues as human Agents. Therefore aspects of the DoView Planning method could be adapted for use with AI agents and human/AI collaboration.
If you look at the DoView methods page and the detailed methods page you will see that there are a number of functions relevant to AI that could be put into a DoView Board used by AI. These include prioritizing boxes for action in any planning cycle, putting indicators onto boxes, putting evaluation questions onto boxes. And checking for alignment. A central issue in human organizational execution is achieving alignment between priority outcomes and activities. This can be done visually and analytically within a DoView Board. Ultimately, this functionality could be built into more advanced DoView Boards. Here is an example of visual alignment visualized in the DoView legacy app.
The components of any outcomes system
Lastly and more theoretically, outcomes theory defines the components of any outcomes system. The diagram below shows the components in any outcomes system. DoView Boards (called DoView diagrams in human organizational practice) can be seen as component A in this framework. They are the underlying source of strategic truth for any outcomes system and DoView Boards are used as the basis for other components.
Outcomes theory is a generic theory relating to taking action in the world, it applies to both humans and AI agents. Therefore we would expect that the development of DoView Boards in the context of AI would involve some of these components.
Design considerations when constructing systems using DoView Boards
Use the DoView Drawing Rules
DoView Boards are not just some random type of box diagram thrown together. They are drawn according to a very specific set of rules. These DoView Diagrams Drawing Rules are used to make sure that DoView Boards are fit for purpose for use in various parts of the planning, prioritization, alignment, delegation, implementation, performance measurement, evaluation and improvement cycle undertaken within any outcomes system.
Break DoView Boards up into subpages humans and parse
DoView Boards are broken up into subpages of a size that are able to be easily understood by human readers and are the right size to be communicated on normal device screens. Each subpage should cover an area that makes sense to humans as a coherent section suitable for dividing into a subpage.
Element that can be included in a DoView Board
A DoView Board should include within it a set of comprehensive set of boxes that mean that it can capture all of the important elements in the strategy space of the particular outcomes system it is part of. For instance, important assumptions and risks (written in the postive) should be included as boxes within a DoView Board. This is so that the one diagram includes everything that needs to be taken into account for planning and implemetation. This is in contrast to some types of drawing logic diagrams which, for instance, exclude risks and represent them in an other type of list (e.g. a risk registry). Details of them could, of course be captured in such a registry, but they should also be represented as boxes within the relevant DoView Board.