AI Requirements Management and Context Setting with OpenRose

Welcome to OpenRose—a free and open-source requirements management tool available at

github.com/openrose

In this blog, we’ll explore how OpenRose’s latest feature empowers users to collaborate with AI platforms like ChatGPT, especially when managing complex projects such as a Charity Fundraising initiative.

Why Context Matters in AI Collaboration

When working with AI—whether it's ChatGPT or any other platform—setting the right context is crucial. This process is known as context engineering or context provisioning, and it’s closely related to what many refer to as prompt engineering.

Rather than overwhelming the AI with excessive or irrelevant data, context engineering ensures the AI receives just the right amount of information—no more, no less. This allows the AI to generate more accurate, relevant, and actionable responses.

As AI systems evolve from simple prompt-based tools into sophisticated autonomous agents, context engineering becomes essential. It helps reduce noise, improve performance, and even enables multi-step task execution without constant human intervention. In fact, poor AI performance is often the result of inadequate context—not flawed models. Think of it like preparing a workspace for a human expert: with the right tools, clear instructions, and relevant background, they thrive. The same principle applies to AI.

Setting the Stage: The Charity Fundraising Project

To demonstrate this, we’ll use a real-world example—a Charity Fundraising project managed in OpenRose. This project includes:

Pre-fundraising preparation
Fundraising event execution
Post-fundraising activities
Parking Lot section for deferred or future items

OpenRose allows users to define custom requirement types, giving full control over how project data is categorized. Once exported in JSON format, this structure becomes instantly readable by AI platforms. I didn’t need to explain every detail manually—ChatGPT quickly understood the hierarchy, relationships, and metadata embedded in the export.

To begin, I identified the project ID for our Charity Fundraising initiative and used OpenRose’s export feature to generate the full JSON output. Once exported, I shared this data with ChatGPT to set the context for our discussion.

Here’s how I introduced the project:

“Hi, I’m a business analyst at a nonprofit charity organization, currently working on a Charity Fundraising event project. We regularly organize events across multiple locations to raise funds and spread awareness. I’ve captured the requirements for our upcoming event using OpenRose. The latest version allows me to export the entire project in JSON format, which I’ll now share with you.”

This message provided ChatGPT with essential context—who I am, what I’m working on, which tool I’m using, and what data I’m about to send. Once the JSON was shared, ChatGPT began analyzing the structure and content of the requirements, recognizing the breakdown across pre-fundraising, event execution, and post-fundraising phases.

Understanding Traceability Through JSON

One of the most powerful aspects of this integration is how traceability is handled. In the JSON export, traceability is represented through IDs rather than names. Despite this, ChatGPT was able to interpret the relationships accurately. For example, it identified that “Monitor Event Progress” is the parent of “Evaluate Success Metrics”—a relationship that exists in my OpenRose repository.

Beyond recognizing existing links, ChatGPT also began suggesting areas for improvement. It flagged missing elements such as completeness checks, risk management plans, and accessibility compliance in the pre-fundraising phase. These insights are invaluable, especially when you're trying to ensure comprehensive coverage across your project lifecycle.

Asking AI to Identify Missing Traceability

With the context now fully established, I asked ChatGPT a more targeted question:

“Given that you know about my project data, can you identify any missing traceability links? Please explain why you’re proposing each link and provide the name and ID of both source and target requirements.”

One of the first suggestions was to link “Plan the Fundraising Campaign” with “Execute the Fundraising Campaign.” While these requirements were already present, they weren’t linked. ChatGPT explained that planning and execution are sequentially dependent, and linking them would ensure that logistics and objectives are properly mapped to implementation. That made sense to me—so I created the traceability link in OpenRose.

This kind of AI-assisted analysis helps me as a business analyst make informed decisions. I can evaluate each suggestion based on feasibility, relevance, and available resources. Not every recommendation needs to be implemented immediately—some can be deferred to the Parking Lot for future consideration.

Identifying Missing Requirements

Next, I asked ChatGPT:

“Now that you know all my existing requirements, are there any missing ones you can identify? Please provide a two- to three-paragraph description and reasoning for each proposed requirement.”

ChatGPT responded with two thoughtful additions:

Volunteer Coordination and Management
This requirement focuses on organizing and managing volunteers effectively. It includes scheduling, assigning roles, and ensuring clear communication. Given that volunteers are often the backbone of charity events, this addition strengthens operational readiness.
Risk Assessment and Mitigation Plan
This requirement emphasizes identifying potential risks—such as weather disruptions, low turnout, or logistical failures—and preparing mitigation strategies. Including this ensures that the project is resilient and adaptable.

These suggestions were well-reasoned and aligned with the goals of my project. I can now choose to incorporate them into OpenRose or park them for future consideration.

Final Thoughts

This experience has shown me how powerful AI platforms like ChatGPT can be when paired with structured data from tools like OpenRose. With just a few steps, I was able to:

Export my project in JSON format
Set the context for AI analysis
Receive actionable insights on traceability and missing requirements
Make informed decisions based on AI recommendations

Whether you're working on a personal initiative, a team project, or a large-scale organizational effort, this approach can help you streamline your requirements management process and unlock new possibilities.

Remember, you don’t always need to export the entire project. OpenRose allows scoped exports, so you can focus on specific sections when needed. This makes it even easier to collaborate with AI and get targeted insights.

Thanks for reading. I hope this blog helps you explore new ways to enhance your projects using OpenRose and AI. Stay tuned for more updates and walkthroughs in future posts.

Have a great day!

OpenRose, a free and open-source requirements management application / tool. For more information, visit

Search This Blog

🌷OpenRose