Artificial Intelligence

SpiraTeam's artificial intelligence functionality empowers you to automate the creation of essential project artifacts from requirements, such as user stories, features, epics, and business/system requirements. It allows you to quickly generate a set of standard test cases, tasks, risks, and BDD scenarios that can then be refined and improved as needed. We have different versions that support different LLMs including OpenAI, Anthropic and Llama, running on platforms such as AWS Bedrock and Azure.

Generative AI Using SpiraApp Plugins

The AI SpiraApps run inside SpiraTeam and provide you with multiple different options of LLMs and AI platforms. We currently offer the options to use OpenAI GPT models running directly on OpenAI or via. Azure as well as a comprehensive set of models from Anthropic and Llama running on AWS Bedrock.

The Generative AI functionality in SpiraTeam lets you:

Take a requirement or user story and generate these common project artifacts:

BDD scenarios and Gherkin syntax

Development tasks for team members

Identify potential risks associated with the product.

It can also suggest potential mitigations for the identified risks.

Create test cases that the testing team can use to successfully test and validate the functionality being created.

The test cases included details steps with expected behavior and relevant sample data

Take an existing test case and perform the following actions:

Reverse-engineer the requirements from the existing test case (useful if the team doesn’t have existing formal requirements documentation)

Create detailed test steps if the test case didn’t already have them

Take an existing development task (either created by the AI or manually) and:

Generate sample source for implementing that feature in a language of the developer’s choosing

Generate sample source code for unit testing the feature using the language and unit test framework of the developer’s choosing

Generative AI Use Cases

For example, imagine that you have just created a new requirement or user story that consists of a single-line such as “As a user I want to book a train between two European cities” or “As a user I want to book a flight between two cities”.

A screenshot of a computer

Description automatically generated

Normally, you would now need to manually write the various test cases that cover this requirement, including positive (can log in successfully) and negative tests (failure to log in for various reasons). In addition, you would need to decompose this requirement in a set of lower-level development tasks for the developers to create the user interface, database, and other items that need to be in place to have a working login page.

If using a BDD approach, you might also want to create a set of BDD Gherkin scenarios that describe each use case for a login page more specifically. Finally, you would want to identify and document all potential risks associated with this new feature.

Using the power of Generative AI, you can radically streamline this approach using the new AI dropdown menus available inside SpiraTeam:

Generating Test Cases

When you click on the option to generate test cases, the plugin will use the configured LLM and create a set of test cases for the requirement in question. For our sample requirement, you can see that it has generated seven test cases, one for the positive case and six additional negative cases:

Each of the test cases consists of multiple detailed test steps that have a description of the action, the expected result if successful, and any sample data if relevant:

Note that the sample data will most likely be very notional since it does not know valid/invalid logins for your application. Still, the overall structure is correct and will save a lot of manual time writing and documenting the test cases.

In some cases, there may be test cases that have been created manually that are missing requirements. For example, the team imported some test cases from a spreadsheet or MS-Word document and now they need to reverse-engineer the requirements. The good news is that the AI assistant can help with this process as well:

When you click on the option to generate requirements, the system will create multiple requirements for the test case in question:

Generating Development Tasks

Next, we can click the generate tasks option to generate five standard development tasks typical for a web login page. You can see that they are relatively high-level but cover the key areas, both the front-end (creating pages) and the back-end (database, session management, authentication system):

Generating Development Code & Unit Tests

Once the tasks have been generated (and for any additional tasks the user manually creates), the user can use the AI Assistant to generate sample source for the current development task.

The user can choose whether to just generate the development code in one of the languages that was specified for the current project, or to generate the development code and the associated unit tests in the matching test automation framework.

Once the source code files are created, they will be displayed in the Attachments tab of the current task.

When a user clicks on the appropriate filename, Spira will display the generated source code, with the appropriate syntax highlighting in place:

A screenshot of a computer program

Description automatically generated

The same is true for the generated unit testing source code as well:

Identifying Risks & Mitigations

Next, we would want to understand the potential business and technical risks of deploying the new functionality. All you need to do is click the generate risks button, and the plugin does the rest:

Once the risks have been identified, the user can click on each risk in term to edit them and make adjustments. In addition, there is additional functionality whereby the AI Assistant can automatically suggest potential mitigations to the identified risk:

This functionality can be used to generate potential mitigations for both AI-generated risks as well as those that were manually identified by the project team:

Generating BDD Scenarios

When using the Behavior Driven Development (BDD) methodology, it is useful to decompose the requirement or user story into different BDD scenarios, both positive and negative. Using the AI Assistant, you can generate a set of BDD scenarios for this requirement, written in the Gherkin syntax. The AI Assistant will automatically convert them into an easy-to-read format with bold for the Gherkin keywords and bullets separating out the components:

In this example, it has created four scenarios, one positive and three negative. Each is written in the Gherkin Given... When.... Then, format and is ready to use.

Generative AI Functionality for AWS Users

SpiraTeam includes a dedicated AWS Bedrock plugin that lets you connect to your own customer instance of AWS Bedrock running in the region of your choice.

All you need to do is specify the URL, region and connection information and SpiraTeam will connect to your LLM instances. We also give you the flexibility to choose your foundational model such as Claude or Llama.

Generative AI Functionality for Azure Users

SpiraTeam includes a dedicated Azure OpenAI plugin that lets you connect to your private deployed LLMs hosted inside Microsoft Azure, accessible via. the same REST API as the public ChatGPT (OpenAI) version.

Since each instance of the OpenAI GPT models is hosted privately inside a customer's Azure environment, you can use the private URL for your own instance of Azure OpenAI. This ensures that you keep control over your sensitive data, while at the same time benefiting from the productivity improvements of Generative AI.