DEV Community

Abdul Qadir
Abdul Qadir

Posted on • Originally published at Medium on

AI-Powered Test Generation: Jira to Xray with CrewAI — Part 1: Setup and Project Overview

#ai #testing #jira #automation

Discover how CrewAI agents can automatically convert Jira requirements into Xray test cases. Includes full setup instructions, project layout, and a ready-to-run GitHub example.

Prerequisites

Before starting this tutorial, make sure you have completed the following setup steps. Each guide walks you through the process from scratch.

These credentials and accounts are required for the CrewAI agents to interact with Jira and Xray.

Required Accounts & API Access

OpenAI API Access

How to Create an OpenAI Account, Generate an API Key, and Add Credits | by Abdul Qadir | Mar, 2026 | Medium

Jira Test Account

How to Set Up a Jira Test Account and Generate an API Key | by Abdul Qadir | Mar, 2026 | Medium

Xray for Jira Setup

How to Set Up Xray for Jira and Generate Client ID and Client Secret | by Abdul Qadir | Mar, 2026 | Medium

Why We Are Using CrewAI?

There are many agent frameworks available today, but CrewAI is a great choice for this project, especially if you’re new to building AI agents.

Key Advantages

Beginner-friendly  — simple concepts and minimal boilerplate

Role-based agents  — define agents with clear goals (e.g., writer, reviewer)

YAML configuration  — behavior can be defined without heavy coding

Fast to prototype  — go from idea to working multi-agent system quickly

Lightweight  — easier to understand than more complex orchestration frameworks

Active community  — growing ecosystem and documentation

In short, CrewAI lets you focus on what the agents should do, not on building infrastructure.

For a project like converting Jira stories into Xray tests, this simplicity makes development faster and much easier for newcomers

Section 1 — Clone the Repository

Start by cloning the public project repository to your machine. This repo contains the full CrewAI project, configuration files, and example code used in this tutorial.

1. Install Git (if not already installed)

Check if Git is installed:

Windows / macOS

git --version
Enter fullscreen mode Exit fullscreen mode

If you see a version number, you’re good to go.

2. Clone the repository

qadir-dev-hub/ai-xray-test-generator

Windows (PowerShell)

git clone qadir-dev-hub/ai-xray-test-generator
cd testcrew_ai
Enter fullscreen mode Exit fullscreen mode

macOS / Linux (Terminal)

git clone qadir-dev-hub/ai-xray-test-generator
cd testcrew_ai
Enter fullscreen mode Exit fullscreen mode

3. Create your environment file

Copy the example environment file:

Windows

copy .env.example .env
Enter fullscreen mode Exit fullscreen mode

macOS / Linux

cp .env.example .env
Enter fullscreen mode Exit fullscreen mode

Open .env and fill in your credentials (Xray, Jira, etc.).

Section 2 — Install uv and Project Dependencies

This project uses uv to manage Python environments and dependencies.

uv automatically creates a virtual environment and installs everything defined in pyproject.toml.

Install uv

Windows (PowerShell)

Run this command:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Enter fullscreen mode Exit fullscreen mode

This will:

Install uv for your user

Add it to your PATH

Require no admin privileges

macOS / Linux

Run:

curl -LsSf https://astral.sh/uv/install.sh | sh
Enter fullscreen mode Exit fullscreen mode

Verify installation

Close and reopen your terminal, then run:

uv --version
Enter fullscreen mode Exit fullscreen mode

If a version number appears, installation succeeded

If uv is not recognized, restart your terminal or log out and back in so the PATH update takes effect.

Install project dependencies

Make sure you are in the project root (the folder containing pyproject.toml), then run:

uv sync
Enter fullscreen mode Exit fullscreen mode

This command will:

Create a .venv virtual environment

Install CrewAI and all required packages

Generate a uv.lock file for reproducible installs

Quick sanity check

If everything installed correctly, you can test Python execution inside the environment:

uv run python --version
Enter fullscreen mode Exit fullscreen mode

You should see Python 3.10–3.13 (as defined in the project requirements).

Architecture Diagram

This diagram shows how a Jira user story is transformed into Xray manual tests using AI agents built with CrewAI.

  1. A user story from Jira serves as the input.
  2. CrewAI orchestrates the workflow between agents.
  3. The Test Case Writer Agent generates initial test cases.
  4. The Test Case Reviewer Agent refines and finalizes them.
  5. A custom tool calls the Xray API to create tests.
  6. Xray saves the manual Test issues back in Jira.

In short, the pipeline automates the flow from requirements → AI-generated test cases → ready-to-use Xray tests , significantly reducing manual effort.

Section 3 — Project Structure Overview

Now that the project is installed, let’s take a quick look at how the repository is organized.

Understanding the project structure will make it much easier to follow how CrewAI agents, tasks, and tools work together to generate Xray test cases from Jira requirements.

A simplified view of the repository looks like this:

testcrew_ai/
├── src/
│ └── testcrew_ai/
│ ├── config/
│ │ ├── agents.yaml
│ │ └── tasks.yaml
│ ├── tools/
│ │ └── xray_tool.py
│ ├── crew.py
│ └── main.py
├── .env
├── pyproject.toml
└── README.md
Enter fullscreen mode Exit fullscreen mode

What each part does

  • config/agents.yaml Defines the AI agents used in the workflow, including their roles, goals, and behavior.
  • config/tasks.yaml Describes the tasks assigned to each agent, such as generating and reviewing test cases.
  • tools/xray_tool.py Contains the custom tool responsible for connecting to the Xray API and creating manual test cases in Jira.
  • crew.py Brings the agents, tasks, and tools together into a CrewAI workflow.
  • main.py Serves as the entry point for running the project.
  • .env Stores the API keys and credentials required for OpenAI, Jira, and Xray.
  • pyproject.toml Manages project metadata and dependencies.

Why this structure works well

This layout keeps the project clean and easy to extend:

  • Configuration is separated from code
  • Agents and tasks are easy to update without rewriting logic
  • External integrations are isolated inside reusable tools
  • The execution flow stays simple and readable

This separation is one of the reasons CrewAI is a good fit for projects like this. You can clearly see where the agent behavior lives, where the business logic lives, and where external systems like Xray are connected.

In the next section, we’ll look at how the agents are defined and how each one contributes to the test generation workflow and how these agents are assigned work through tasks.yaml, and how the overall process moves from Jira requirements to Xray-ready test cases.

Read part 2 here — https://dev.to/abdul_qadir/ai-powered-test-generation-jira-to-xray-with-crewai-part-2-agents-tasks-and-xray-integration-3jid

Top comments (0)