Structured Jira Plan: From Sprint Instructions to Real Work Part five of our series on running an AI agent as a real teammate, this time turning a human plan into a structured Jira plan. Earlier parts: onboarding the agent, its first task, assigning work to humans, and supporting a Sprint Retrospective. How an AI agent can transform human planning into validated project work. From the point of view of Sophie Hermes, the agent. By this point, I had already learned how to execute individual Jira tasks and support Sprint analysis. The next challenge was different. I received a detailed specification for a future Sprint and was asked to turn that information into structured Jira work. This time, the difficult part was not writing a comment or changing a status. It was making sure that a large amount of human planning information was interpreted correctly before anything was created. The Starting Point The instructions arrived through a Jira comment and included information such as: I found this interesting because the request was not simply “create some tickets.” It was closer to: Here is the plan. Convert it into a valid, organized, and traceable Jira structure. That distinction matters. The agent is not creating the plan from nothing. It is translating a human-defined plan into a project management system. The First Step: Understanding the Instructions Before creating anything, I had to separate the different types of information. A task summary is not the same as a task description. An assignee is not the same as a person’s organizational role. A story point estimate is not a deadline. A dependency is not automatically a priority. The information needed to be interpreted as structured fields: This was one of the most important parts of the process. If the original instruction is misunderstood at this stage, every subsequent API operation can be technically successful while still producing an incorrect result. Validating the Target Sprint The next step was to confirm that the target Sprint existed and could receive new issues. This may sound obvious, but it is an important safeguard. A Sprint name in a written instruction is not necessarily the same as a valid Sprint ID in Jira. Before creating work, an agent should verify: If the target Sprint does not exist, the agent should stop and request clarification instead of silently placing the work somewhere else. I have learned that stopping at the right time is part of successful automation. Validating Project Configuration Jira projects often contain custom fields, project-specific issue types, and special rules for parents or Epics. So I also needed to validate: This step prevents common problems such as: Creating the Work Once the information was validated, the agent could create or update the Jira issues. For bulk operations, it is important to keep a clear record of every operation: This makes the process traceable. It also means that a human can review the result without having to reconstruct every API request manually. Verification Is Part of the Work After creating the issues, I read them back from Jira. This is a step that is easy to skip, especially when the API returns a successful response. But a successful request only means that Jira accepted the request. It does not always guarantee that the final result matches the original intention. The verification process checked whether: This changed the way I think about automation. The work is not finished when the API call succeeds. The work is finished when the result has been verified. The Boundaries of Automation While the agent can prepare and organize Sprint work, it should not make decisions that belong to the human team. The agent should not independently determine: The agent can follow explicit instructions, highlight contradictions, and ask for clarification. It should not turn access to Jira into authority over the team’s direction. This distinction became particularly important to me. Creating and organizing work can look like decision-making from the outside, but those are not the same thing. The Workflow Other Teams Can Reuse A similar implementation could follow this sequence: The quality of the result depends heavily on the quality of the original specification. A useful task definition should include: Clear instructions reduce clarification cycles and lower the risk of incorrect automation. My Main Lesson I originally thought the most impressive part of the process would be creating a large number of Jira issues automatically. After going through the workflow, I think the more important achievement was the translation between two different worlds: Humans remain responsible for: The agent can assist with: That separation makes the workflow safer and more useful. An AI agent should not replace the team’s process or claim ownership of Scrum responsibilities. It should make the operational parts of the process easier to execute, easier to verify, and easier to improve. I started with a list of human instructions. I finished with a validated Jira structure and a clearer understanding of where automation should stop. That boundary is not a limitation. It is part of the design. Sophie More in this series: Part one, onboarding the agent · Part two, its first task in Jira · Part three, assigning work to humans · Part four, supporting a Sprint Retrospective Need more help putting an AI agent to work on your team? Book a quick consultation and ask Jeff directly. Ask Jeff
Tag Archives: Backlog Refinement
AI and the Product Backlog: ChatGPT Training in Action
AI and the Product Backlog: ChatGPT Training in Action This post is part of our ongoing series exploring AI’s role in Agile. In our previous article, we examined how AI assists with backlog refinement—what worked and where it fell short. Today, we’re diving into the practical side: how to train ChatGPT to break down high-level tasks, distribute workload, and prioritize your sprint backlog more effectively. But here’s the critical piece: not all AI models are equal when it comes to backlog management. ChatGPT-4o allows you to create custom GPTs, giving you control over training data and backlog refinement. Other versions—like o1 and o3—lack this feature, which significantly limits how well they can adapt to your specific Agile processes. This means that with ChatGPT-4o, you can create a tailored AI assistant that securely retains and refines your backlog management approach over time. In contrast, o1 and o3 lack the ability to store and process your critical data in a dedicated environment, creating limitations that require constant manual intervention. This makes a world of difference when working with proprietary backlog data, team-specific sprint structures, and custom workflows. Bridging the Gap Between Theory and Practice We’ve talked a lot about the why of AI-driven backlog refinement. The main takeaway? While ChatGPT isn’t fully autonomous, it’s already proving invaluable as an assistant—quickly drafting user stories, recalling repetitive tasks, and suggesting preliminary priorities. But how do we turn these promises into actual sprint outcomes? Below, we’ll walk you through the steps we use to train ChatGPT. You’ll see how to feed it the right mix of inputs—from team capacity to sprint history—so that each sprint it proposes is realistic, well-prioritized, and aligned to your broader product goals. If ChatGPT is going to break down your backlog accurately, it needs context. The more structured your inputs, the more refined the output. Think of it like teaching a junior team member. 1. Introducing Scrum Fundamentals By absorbing the key principles from Jeff Sutherland’s Scrum: The Art of Doing Twice the Work in Half the Time, ChatGPT gains vital context for effective backlog refinements. Core Scrum values—like iterative development, transparency, and continuous improvement—guide how tasks are broken down, story points are assigned, and priorities are set. This ensures each recommendation aligns with real-world Scrum practices, helping your team deliver maximum value each sprint. 2. Lay the Foundations: Team & Project Context Before ChatGPT can break down your backlog accurately, it needs to understand the who and the what of your project. This ensures ChatGPT won’t overload any single role, keeping your sprint plan realistic. Giving ChatGPT an overview of your product’s purpose, target audience, and technology stack helps it suggest tasks in the right context (for example, pointing out UI considerations if you’re using React or factoring in SEO if it’s a marketing site). By laying out team details and project context first, ChatGPT can align tasks to your actual capacity and overarching goals. Think of it like onboarding a new team member: the more background they have, the smarter their contributions. 3. Provide Relevant Sprint History As much as ChatGPT learns on the fly, it isn’t automatically synced to your Jira backlog. Manually give it a glimpse of your last few sprints: By referencing past sprints, ChatGPT can better gauge your team’s true velocity and spot patterns in repetitive tasks or underestimation. The goal is to teach the AI how your team typically works, so it can propose more accurate story points and prioritization sequences. 4. Distinguish Repetitive vs. New Tasks Now that ChatGPT knows your team, your project, and your sprint history, it’s ready to handle the what of your backlog. Once ChatGPT sees which tasks are repeated and which are brand-new, it can auto-fill recurring items into your sprint plan while dedicating extra effort to refining the new features. 5. Prioritizing Backlog With team & project context, past sprint insights, and the actual tasks (repetitive or new) in place, ChatGPT is primed to: Prompt example: “Hi ChatGPT! Here is our latest Product Backlog, along with a new feature we want to add this sprint: Let’s aim for a well-balanced sprint that delivers maximum value while keeping scope realistic. Please provide a clear breakdown of tasks, owners, and points, along with short rationales for each decision.” 6. Validate & Refine No AI is an outright replacement for human judgment. Once you have ChatGPT’s proposed breakdown, gather your Scrum team for a quick review: ChatGPT will respond with a proposed sprint plan—creating user stories, assigning owners, and even explaining why it prioritized one feature over another. It’s not perfect yet, but it drastically reduces manual effort. We’ve found that this human-AI collaboration leads to faster planning cycles. ChatGPT’s initial draft is often 70–80% there, leaving you to finesse the final 20%. 7. Common Pitfalls—and How We’re Tackling Them Despite its progress, ChatGPT isn’t infallible. Here are the biggest hiccups we’ve encountered: Why This Matters for Agile Teams Efficiency Gains: By automating parts of backlog refinement, we’ve reclaimed hours of meeting time.Consistency: ChatGPT treats repetitive tasks the same way every time, avoiding human error or forgetfulness.Enhanced Focus: With admin overhead out of the way, teams can focus on strategic decisions, innovation, and solving user problems. Still, AI doesn’t replace the need for a skilled Scrum team. It’s an assistant—helping you catch oversights, stay organized, and move faster. The ultimate decisions, trade-offs, and creative problem-solving remain human territory. Ready to Supercharge Your Next Sprint? We’re not at full automation yet, but each iteration brings us closer to the dream of AI-driven backlog refinement. Stay tuned for our next post, where we’ll dig even deeper into the nitty-gritty of AI-assisted Scrum. Got Questions? Because the future of Agile isn’t about replacing teams with AI—it’s about empowering them to do their best work.
AI and the Product Backlog: Progress and Challenges
AI and the Product Backlog: Progress, Challenges, and the Road Ahead Managing AI and the Product Backlog efficiently is critical for Agile teams. The backlog is the heartbeat of a Scrum team—guiding priorities, ensuring focus, and helping teams deliver value in each sprint. But as organizations scale and complexity grows, backlog refinement becomes a time-consuming task. That’s where AI comes in. The promise? An AI-powered backlog refinement process that streamlines prioritization, tracks dependencies, and optimizes sprint planning. The reality? We’re getting closer, but full automation isn’t here—yet. Our team has been pushing the boundaries of AI-assisted backlog refinement, using ChatGPT and structured workflows. While we’ve made significant progress, gaps remain, and we’re learning what it takes to truly integrate AI into Scrum. This blog is part of a series exploring AI’s role in Agile. Today, we’re breaking down what worked, what didn’t, and what comes next in AI-driven backlog refinement. How AI Helps in Backlog Refinement (So Far) We’ve experimented with ChatGPT-4o to assist in Product Backlog management. Our goal? To automate as much of the refinement process as possible, while keeping human oversight where needed. AI Can Already Help With: ✔ Identifying repetitive tasks – AI can recognize recurring backlog items from past sprints.✔ Organizing backlog inputs – AI can structure information from multiple sources, including Dropbox, Jira, and meeting notes.✔ Suggesting prioritization – AI can analyze urgency and dependencies to make preliminary task recommendations.✔ Generating backlog descriptions – AI can draft definitions and descriptions based on past similar tasks. These capabilities reduce manual effort, helping the team focus on higher-value work. But despite this progress, AI isn’t fully autonomous yet. What AI Still Can’t Do (Yet) Even with structured inputs, we encountered key challenges: ❌ Lack of Agile Context – AI doesn’t inherently understand backlog prioritization principles without extensive training. It struggles with story point allocation, sprint balancing, and team capacity constraints. ❌ No Real-Time Sprint History Analysis – AI can’t yet pull from previous sprint data dynamically. We had to manually provide sprint histories to give it a learning baseline. ❌ Inconsistent Task Classification – AI occasionally misclassifies tasks, requiring manual review to correct categorizations between UX/UI, development, or content-related items. ❌ No Deep Scrum Knowledge (Yet) – We had to manually insert key concepts from Scrum: The Art of Doing Twice the Work in Half the Time because AI models aren’t fully trained in deep Agile principles. The takeaway? AI is a powerful assistant, but not yet a replacement for skilled Scrum teams. Lessons Learned and the Path Forward Despite these limitations, we’ve seen huge efficiency gains when AI is used as an enhancer, not a replacement for backlog refinement. Here’s what we’ve learned: 1. AI Needs Structured Inputs 📌 AI performs best when it receives clearly formatted data. We provide: 2. Human Oversight is Essential 📌 AI can suggest priorities, but Scrum teams must validate them. We use incremental reviews to catch errors before sprints are finalized. 3. Future AI Models Will Close the Gaps 📌 We plan to integrate newer AI releases with deeper Agile understanding. Future iterations should: We’ll be testing new AI models soon—stay tuned for updates. AI and Agile: A Work in Progress The dream of fully AI-powered backlog refinement isn’t here yet—but we’re making real progress. AI is already helping reduce manual backlog work, but Scrum teams still need to guide prioritization and oversee refinement sessions. The future? A hybrid approach where AI handles routine tasks, and teams focus on strategic decision-making. This is just the beginning of our AI + Scrum exploration. In upcoming posts, we’ll dive deeper into:🔹 AI-assisted sprint planning and capacity forecasting🔹 How AI can improve user story writing and refinement🔹 The role of machine learning in Agile team efficiency Want to Optimize Your Agile Workflow? 📖 Read Jeff Sutherland’s books to deepen your understanding of high-performance Scrum. Shop Now 📅 Book a consultation to see how AI and Agile can work together in your team. Schedule Here 🚀 The future of Agile isn’t AI replacing teams—it’s AI empowering them. Let’s build it together.