Using Jira Custom Fields in Release Notes

Ever found yourself wishing you could squeeze a bit more information into your release notes? You’re not alone. While Released gives you the flexibility to choose your description field, sometimes you need to pull in details from other fields—like documentation links, product areas, themes, or even customer names. The good news? There’s a straightforward workaround to make this happen until we roll out native support. Let’s dive in!

Copy fields with Jira automation

Released currently supports referencing a single text field for AI-generated content. However, with Jira automation, you can automatically copy additional fields into that text field—making them available for AI as well.

1. Copy Field Values: Use Jira Automation to pull in values from other fields into your description field.

2. Adjust Your AI Prompt: Reference those fields in your AI prompts to ensure everything flows smoothly.

Let’s break it down step by step.

Setting up the automation

First things first, you need to decide how you want to trigger this automation. You’ve got a couple of solid options:

• Manual Trigger: Run the automation on demand whenever you need it.

• Workflow Transition Trigger: Automatically kick off the automation when an issue’s status changes.

Once you’ve got your trigger set up, it’s time to define the action. In this case, we want to edit the description field used for generating release notes. Here’s a quick example of how to structure it:

{{issue.description}}

### Other Information

Assignee: {{assignee.displayName}}  
Versions: {{issue.fixVersions.name}}  
Documentation: {{issue.customfield_10414}} // Note: the custom field ID will differ.

This format keeps your original description intact while adding a new section for additional details. It’s neat, organized, and easy to reference in your AI prompts.

Referencing fields in your prompt

Now that you’ve got the data in your description field, it’s time to make it work for you. When crafting your AI prompt, simply use the field names as you’ve structured them. This ensures that the AI knows exactly what to pull and how to present it.

For example, let’s say you’re working on a Jira issue with the following description:

Title: Implement Automatic Change Logging for Task Tracking

Description:
We plan to enhance the task tracking feature by implementing automatic change logging. This improvement will allow users to see a complete history of changes made to tasks, including updates to assignees, due dates, and status changes. Once completed, users will be able to easily track task progress and accountability, leading to better project management and collaboration.

Other Information

• Assignee: Jane Doe

• Support tickets: JRA-456, JRA-789

• Module: Tasks Tracking

• Documentation: Task Management Docs

Creating great release notes is all about balance—providing enough detail while keeping it easy to read. A well-crafted prompt can help you generate release notes that mix clear, natural language with structured information.

Here’s an example of a prompt that does just that: it starts with a concise summary in prose, followed by a structured section for key details. This approach ensures that readers quickly grasp the main update while still having access to all the relevant information.

Use the following guidelines:

1. General Tone and Style:
- Use clear, concise language that is easy for end-users to understand.
- Highlight the benefits of changes, improvements, or fixes.
- Minimise technical jargon unless it is essential for accuracy.

2. Content Structure:
<h3> [Title]</h3>

<p>[Description]</p> 
<!-- Write a single paragraph that: -->
<!-- - Describes what was improved, added, or fixed (<Improvement/Change Summary>). -->
<!-- - Explains the impact or benefits for the end-user (<End-user Benefits>). -->

<h4>Other information</h4> <!-- Only show this section if there is other information available. -->
<ul>
<li><b>Assignee:</b> [Assignee name] </li> <!-- Omit if no assignee is set -->
<li><b>Support tickets:</b> [Linked support ticket IDs]</li> <!-- Show IDs only. Eg: JRA-123, JRA-124 -->
<li><b>Module:</b> [Customer name] <!-- Omit if value is "Select Customer" or unavailable. -->
<li><b>Learn more:</b> [Documentation link] 
</ul>

It starts with tone and style instructions, followed by a clear content structure: a description at the top and a structured “Other Information” section below.

You can also include specific instructions for different scenarios, such as how to handle missing values.

Finally, use the preview available in the "Issue specific prompts" section to test your prompt with a few issues and verify that the AI generates the desired output.

Additional tips

To ensure your AI outputs are structured and reliable, consider these extra tips:

• Be Specific: Clearly define what you want in your prompt. The more specific you are about the structure and content, the better the AI can follow your instructions.

• Use Examples: Providing examples of the desired output can help the AI understand the format you’re looking for. This can serve as a template for the AI to mimic.

• Break It Down: If the output requires multiple sections, break down the prompt into smaller, manageable parts. This helps the AI focus on one section at a time.

• Reiterate Key Points: If certain elements are crucial (like including a title or specific details), reiterate these points in your prompt to emphasize their importance.

• Test and Iterate: Don’t hesitate to test different prompts and refine them based on the AI’s responses. Iteration can help you find the most effective way to communicate your needs.

• Encourage Clarity: Remind the AI to prioritize clarity and conciseness in its responses. Phrases like "keep it simple" or "make it easy to understand" can reinforce this.

• Limit Jargon: Specify that the AI should minimize technical jargon unless necessary. This helps ensure the output is accessible to a broader audience.

And that's how easy it is to include custom fields in your release notes. Enjoy!