BETA

This page reflects the AI Guidance Beta version and will be updated as the feature continues to evolve. Please note that some UI/UX elements may slightly change by the final release.


Introduction

AI Guidance, a feature in Xray Enterprise Test Case Designer (TCD), powered by Sembi iQ, accelerates one of the most critical steps in the modeling process: creating an initial draft of Parameters and Values. It supports both new users learning the Test Case Designer approach and experienced testers working with complex or extensive documentation, helping them move faster from raw inputs to a structured model.

Feature Scope

  • Currently BETA

  • AI Guidance can be enabled or disabled at the user level per request (CONFIRM).
  • There are five AI Actions available.
  • Accessible only in the Regular view of the Parameters screen, not in the Bulk mode.

Key Benefits

  • Accelerates modeling by quickly generating Parameters and Values.

  • Accepts a variety of text-based formats with minimal preparation.
  • Understands advanced testing techniques like boundary testing and equivalence classes.
  • Adapts to your iterative process, with AI actions using the model’s evolving state as additional context.
  • Does not disrupt the workflow by being fully integrated right into the Parameters screen, with a dedicated UI that keeps you in control. 

Operations

Access

AI Guidance is a part of Xray Enterprise Test Case Designer. You can see here how to access, configure, and use it.

Managing Access

If you are an organization Admin, you can click your profile name (Figure 1 - 1) and open the Organization Settings (Figure 1 - 2) from the menu.

Figure 1 - Admin

Figure 1 - Admin

Click Organization Settings (Figure 2 - 1).

Figure 2 - Organization

Figure 2 - Organization

A pop-up will open (Figure 3). There, click Edit Organization (Figure 3 - 1).

Figure 3 - Organization 

Figure 3 - Organization Settings

In addition to filling in the Email domain list (Figure 4 - 5), you can now check the Enable AI suggestions box (Figure 4 - 1) to control the overall AI availability for your organization.

Figure 4 - Edit

Figure 4 - Edit Organization


You can set the Default file expiration (Figure 4 - 2; “0” means files do not expire) and the File expiration max (Figure 4 - 3). Any user in your organization cannot exceed that max value in their model settings, but they can set a value lower than the default, as well as enable expiration when the default is “0” (Figure 4 - 2).

Once you're finished, click Update Organization (Figure 4 - 6). 

When the Enable AI suggestions box is checked (Figure 4 - 1), the column below (Figure 5 - 1) becomes editable in the User Management view. There, you can enable or disable individual accounts based on your preferences.

Figure 5 - User-level AI Permissions

Figure 5 - User-level AI Permissions


AI Actions 

AI Guidance is available for five specific actions within the Parameters section, exclusively in the Regular view (Figure 6 - 1). This feature is not accessible when working in Bulk view (Figure 6 - 2).

1 - Suggesting Initial Parameters

 In a new, empty model (Figure 6), click the Generate Parameters (Figure 6 - 3) button to create a set of initial Parameters.
Figure 1 - Parameters

Figure 6 - Parameters screen in an empty model


2 - Adding Parameters to an Existing Model

Click the Generate Parameters button (Figure 7 - 1) at the end of your current Parameter list to expand your model with additional Parameters.

Figure 7 - Parameters screen in a non-empty model

Figure 7 - Parameters screen in a non-empty model

Both Action 1 and Action 2 will often return no more than 10 Parameter candidates per request. If you are expecting a larger model, you would need to trigger Action 2 a couple of times. See more details in the How it Works section below.


3 - Generating Values for a New Parameter

This can be useful if you know that a certain element is missing but do not know its details. 

Add the Parameter Name (Figure 8 - 1).

Figure 8 - Parameter name

Figure 8 - New Parameter dialog

Click Generate parameter variations (Figure 8 - 2) to add Value types using AI Guidance.

Once you're done with accepting and/or rejecting suggestions, click Create (Figure 8 - 3).

4 - Expanding Parameter Values

 Hover over any existing Parameter name and click Suggest more parameter values (Figure 9 - 1) to increase the selection of Test values.

Figure 9 - Increasing the number of parameter values

Figure 9 - Increasing the number of parameter values

5 - Reducing Parameter Values

Hover over any existing Parameter name and click Suggest fewer parameter values (Figure 10 - 1) to streamline and focus the Test scope.

Figure 10 - Reducing the number of parameter values

Figure 10 - Reducing the number of parameter values

  • Action #3 will NOT be shown if the AI Guidance modal is missing a goal or an upload (see more in the next section below).

  • The availability of actions #4 and #5 adapts dynamically based on how many values your Parameter currently has. The breakpoint is set at five values. Parameters with five values or fewer will default to expanding suggestions; those with six or more values will focus on reduction.


How it Works

The process is flexible and iterative. Whether you are starting with the AI-generated draft or the manually created model, you can leverage the different AI actions and consider adjustments to the Testing goal and system documentation to continue refining your model until it is ready for testing.

The typical, initial set of steps could follow the pattern below:

Stage 1 - Context Setup

Create a new, empty model and click the Generate Parameters button (Figure 11 - 3). 

 Figure 11 - Generate

Figure 11 - Action 1 example

To use AI Guidance, you must provide two essential pieces of context (Figure 12 - 1):

  • A high-level Testing goal of at least 10 words that clearly articulates the scope and objectives of your modeling effort.
  • Relevant documentation about the system under test in supported formats, with each file not exceeding 50 MB. More below.

Figure 12 - Guidance

Figure 12 - Guidance

Once you click Yes, provide guidance (Figure 12 - 2), you will be redirected to the dedicated AI modal (Figure 15).

 You can also get to the AI modal (Figure 15) directly by clicking the AI Guidance icon in the left menu (Figure 13 - 1) or the one next to the model name (Figure 14 - 1).

Figure 13 - Menu

Figure 13 - Left vertical menu


Until both parts are provided (Figure 12 - 1), you will see the red dot next to the AI Guidance icon in the top ribbon (Figure 14 - 1).

Figure 14 - Dot

Figure 14 - Top ribbon with the notification dot


On the left side of the modal (Figure 15 - 1), you must provide a high-level Testing objective, describing the scope of what you aim to achieve with this model. 

For instance, if you were testing the Monopoly game implementation, it could be something like (Figure 15 - 1): “Ensure the system correctly implements the rules of Monopoly. Focus heavily on the rules regarding money changing hands between players and player bankruptcy, and game ending scenarios".

Figure 15 - Modal

Figure 15 - Modal


- For a quick refresher without leaving the AI Guidance modal, open the Usage section (Figure 15 - 7).

- We recommend uploading files first, then specifying the testing goal (because the files take a bit of extra time to process, even after the upload spinner has disappeared). You may encounter a 15-second timeout message if the files require more time.


On the right side of the modal (Figure 15 - 2), you must add the majority of your source documentation in several formats. 

TCD strives to make this tool as flexible as possible, so that you don’t have to do extensive data cleaning or reformatting. This feature also expands TCD's import flexibility beyond strictly formatted Excel files or mind maps.

The AI Guidance initial release will only support text-based documents. AI Guidance extracts and processes only textual content from your documentation. For instance, if you provide a PDF or PPT file with a mix of text and images, only text portions will be analyzed. Files consisting entirely of non-text content, like images (JPG, etc.) or videos (MP4, etc.), will be ignored by the system.

OPML mind maps are currently not processed by AI. So, you can either import these files directly into the model creation dialog or convert them, for instance, into XML for AI.

 There are two ways to add the documentation (Figure 15 - 3):

  • Uploading (when you already have a compiled file).
  • Typing/Pasting (when you have bits and pieces and want AI Guidance to compile the file for you).

Both ways are treated the same way for AI processing. The order of uploads is not relevant. You cannot download attachments (uploaded by you or other users).

You have the option to configure automatic file deletion after a specified timeframe (Figure 15 - 4). This setting only applies to future uploads - it doesn't affect files already added to your model. If you upload a file with expiration disabled and want to enable it later, you'll need to manually delete the existing file and reupload it with the expiration setting activated. As mentioned above, this option respects the Organization-level settings. To remove the file manually, hover over it and click the trash icon (Figure 15 - 6).


Stage 2 - Generating an Initial Draft and Reviewing

With both context elements in place, close the Guidance modal by clicking Confirm (Figure 15 - 5).

Click the Generate Parameters button (Figure 16 - 1) again to initiate the AI process.

Figure 16 - Parameters

Figure 16 - "Generate parameters" loading screen

You will enter a screen with the suggested set of key model elements - Parameters and Values (Figure 17). 

Figure 17 - Parameters

Figure 17 - Parameters

This screen (Figure 17) is very similar to the TCD's Parameters screen. However, it works as a subspace for reviewing purposes only. You cannot directly edit Parameters or Values, and if you try to navigate away, you will see the following warning (Figure 18):

Figure 18 - Warning

Figure 18 - Warning


While regenerating the suggestions is fast and easy, AI results are generally not 100% consistent. It's recommended to finish the review before doing anything else in the model.

There are a couple of things to highlight for this stage:

  • The AI is aware of techniques such as equivalence classes and boundary Testing that are connected to TCD's Value Expansions and Ranged Values, so they can be added to the suggestions when the AI "deems" it appropriate.
  • You can reject individual Values, accept/reject the whole Parameter, and accept/reject the entire set via the Bulk options at the bottom (Figure 17 - 1).
  • Only when all the review decisions are made, the screen will change to the Regular Parameters view that allows you to perform any typical modeling actions like editing Parameters/Values, navigating to Rules or Scenarios, etc. (Figure 19).

Figure 19 - Parameters

Figure 19 - Parameters


Stage 3 - Refining and Iterating

AI Guidance operates as an intelligent assistant, presenting suggestions for your consideration (rather than making any immediate changes to your model). You maintain full control, reviewing each suggestion and deciding whether to accept or reject it based on your expertise and Testing Requirements.

Once you're satisfied with the AI's suggestions, you don't need to repeatedly specify the Testing goal and system documentation for subsequent AI actions. The AI also maintains awareness of your model's current state, automatically considering any manual changes you make when generating future suggestions.

When initial suggestions miss the mark or you need a different focus for subsequent actions, simply return to the AI Guidance modal (Figure 15) to modify your Testing goal or system documentation. This flexibility ensures the AI stays aligned with your evolving needs. Action #2 (Additional parameters to an existing model) offers an additional modal (Figure 20) where you can specify a more targeted coverage goal to guide the AI's exploration of specific Requirement areas (Figure 20 - 1). For instance, in the Monopoly example, that additional goal could be “Test the scenarios for a player getting out of jail”.

Once you're finished, click Generate Parameters (Figure 20 - 3).


Figure 20 - Additional parameters

Figure 20 - Additional parameters


  • You can use the Pre-fill option (Figure 20 - 2) to automatically copy the Testing goal from the AI modal (Figure 15 - 2).
  • Adding more specific wording to the Testing goal (e.g., “telehealth scheduling scenarios”) can help the Large Language Model (LLM) pull extra aspects from the foundational knowledge pool, but it can also introduce elements that are too generic or invalid/irrelevant for your particular scope. Experimentation is required to find the right balance in the goal wording based on your use cases.
  • For more complex Test models, it can be helpful to intentionally “feed” context to the AI incrementally: start with the core Testing goal and the most important documents, then execute the initial generation in an empty model. Make any manual corrections as needed. Next, upload additional documents and use the extra Testing goal modal (Figure 15) to guide the AI towards a deeper exploration of specific elements. While the goals you provide are not used directly as prompts (Xray handles prompt engineering in the background, so you don’t need to worry about that), the overall approach is conceptually similar to chain prompting.


Limitations

  • Text formatting is not considered for AI processing (e.g., a crossed-out paragraph would still be analyzed).
  • AI Guidance API has a limit of total requests on a monthly basis, 250 per user account (each AI action = 1 request; it resets on the 25th of each month). CONFIRM
  • For future releases, Xray is evaluating the AI applicability to Scripts and Rules as well. For this one, to avoid any doubts, your interactions with other screens (Rules, Scenarios, etc.) don’t change.
  • At least in the initial release, Xray will not be offering additional LLM training or fine-tuning options, i.e., uploaded system documentation is not used to change/update the LLM behind the scenes, it is only used as context for parameter & value generation. However, AI is receiving the initial goal and documents as well as the latest model content for each request, so it can gradually make better suggestions.



For more information, please contact your Customer Success Manager and/or the Xray Support team via the Customer Portal (Jira service management) to access Xray's Compliance Portal for the AI security white paper.

  • No labels