> For the complete documentation index, see [llms.txt](https://helpdocs.conducttr.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpdocs.conducttr.com/feature-documentation/planning/active-exercise-system-axs/canvas.md). # Canvas Canvas is a **brainstorming AI tool which provides a one-page overview of all the important areas of an exercise**. It allows you to develop an idea and present it for client sign-off. You can then export to a serial file and generate injects inside your Editor. | Benefit | Feature | | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | Fast and efficient way to explore crisis ideas and present for sign-off | | ## The Canvas project page The Canvas landing page will show you all your Canvas projects.
## Create a new Canvas * On the dashboard, click `Create Project` * Give your project a name * Add an image and related description to the project (optional) * Add project tags (optional)
## How to generate an exercise {% stepper %} {% step %} ### Enter initial idea or news article * Click `Get started`, and write a prompt to generate a scenario * Select the number of acts you want there to be in your scenario (3 or 5 acts) {% hint style="success" %} * Acts corresponds to Serials in the Editor * You also have the option to incorporate URL's into the prompt - where the news source allows it. For example your prompt could be: "focus on the role of the bank risk manager" " * If pasting the URL doesn't work, copy-paste the article instead {% endhint %} {% hint style="warning" %} You'll get better results if you mention who the players are because then the AI can frame the scenario from this perspective {% endhint %} Most stories are 3 act structures and this is sufficient for business continuity exercises of about an hour or less. If you want additional granularity in your exercise structure or for longer exercises, you might find a 5 act structure works best.
{% endstep %} {% step %} ### Confirm AI result or edit * Click on the "magic icon" (sparkles) to generate your scenario * If you're not happy with the story created, you can re-click the assistant again and it will generate something new * If you're happy with the story, click on `Create summary` > `Submit summary`
The scenario and the summary are used to generate the rest of the Canvas so be sure you're happy with it before moving on. You can manually edit it too. {% endstep %} {% step %} ### Complete the rest of the Canvas You then have 2 options to complete the Canvas: 1. **Complete the whole Canvas at once** by clicking `Complete Canvas` > `Fill in Canvas` (this will auto-complete all boxes within the Canvas) 2. **Complete individual boxes** by clicking the "magic icon" next to each box to auto-complete that specific box
While you'll see a one-page summary of the whole exercise, click into a field to reveal the details. * Click into a box to view a more detailed explanation * In the example below, *Roles and Positions* has been clicked on, and has opened up the detailed view on the right * To edit any of the details, just simply click into the text and make changes. Ensure to click `Save` to save any changes made
{% endstep %} {% step %} ### Export to Editor After the initial scenario has been created you can export a .csv file of the Serials. These can be imported into the Editor.
And here's the Editor view where you import the exported Serial file.
{% endstep %} {% endstepper %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://helpdocs.conducttr.com/feature-documentation/planning/active-exercise-system-axs/canvas.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.