Summary
Challenge: Manual test script creation is time-consuming and error-prone, with QA teams spending too much time on repetitive tasks. This slows testing cycles, impacts delivery speed, and leads to inconsistencies.
Solution: A custom Forge-built Rovo agent automates the test suite lifecycle by pulling data from Jira and Confluence. It generates test scripts, cycles, and plans in Zephyr Scale, with users interacting through natural language prompts.
Outcome: This reduces manual effort, speeds up QA cycles, and improves accuracy. It enhances traceability, supports compliance, and allows teams to focus on quality, leading to faster delivery and better customer outcomes.
Background
Here at AC, we wanted to address a persistent source of frustration for many Quality Assurance (QA) professionals: Creating test suites.
Instead of being straightforward, this process is often bogged down by repetitive, manual tasks, which is a real drain on productivity.
As such, we built a custom Rovo Agent to automate test suite creation and accelerate Quality Assurance.
Challenge
From writing test scripts, creating and linking test cycles, and grouping everything into test plans, the steps behind creating a test suite are almost aways manual.
Testers spend valuable time copying and pasting information, double-checking links, and repeating the same steps for every new story or bug fix. The result? Less time for actual testing and quality improvement, increased risk of errors and inconsistencies, and slower, less reliable feedback loops for agile teams.
Solution
Recognising the opportunity to transform the QA process, we asked: What if we could automate the entire workflow – from extracting acceptance criteria to creating and executing test cases, and even feeding results back into Jira for traceability?
Inspired by this vision, we created a custom Forge-built Rovo agent that provides a solution to automate and streamline the entire test suite lifecycle, fundamentally changing the way QA teams work.
How this custom Rovo Agent works
At its core, the Agent automatically pulls information from Jira tickets (acceptance criteria, comments and custom field information) and uses this data to build a comprehensive test suite in the Zephyr Scale Jira app.
The agent also taps into linked Confluence documentation, intelligently extracting additional feature information and other non-functional requirements to generate robust, meaningful test cases, regardless of ticket format or documentation style.
The agent reads and interprets information from both Jira and Confluence, extracts acceptance criteria and supporting information, and then creates the necessary test cases, cycles, and plans in Zephyr via API calls. It can even monitor test execution, and is designed with future integrations in mind, such as linking up with reporting tools like eazyBI, PowerBI, or Tableau for advanced analytics.
Intuitive user experience
The user experience was designed to be intuitive. Testers and managers can interact with the agent using natural language prompts, such as Generate a test suite for all stories in ‘Ready for Test’, or Create positive, negative, and edge case test cases for Work Item X.
The agent can also summarise testing coverage, show test plans and cycles for specific tickets, and update Jira with the latest test results from Zephyr.
This seamless integration between Jira, Confluence, and Zephyr is orchestrated entirely through APIs, laying the groundwork for even more advanced reporting and analytics in the future.
Benefits
By automating the most repetitive and error-prone parts of the QA process, we’re freeing up testers to focus on what they do best: finding bugs and ensuring quality.
The reduction in manual effort is significant, with test cases and cycles being generated automatically rather than by hand. This speeds up the transition from ticket status change to test execution, and improves the overall quality of the product, which will always leads to increased customer satisfaction.
Teams will have the ability to measure success in several ways: the time saved on test case creation and execution, the number of test cases and cycles generated automatically, and the speed at which feedback is delivered to developers and project managers – all of which speed up the overall delivery of a product or project.
