Scrum in the Era of Agentic Software Development

 Agentic coding, where AI-driven agents autonomously write, test, debug, and refactor code, represents a significant shift that could substantially impact traditional Scrum practices. Far from a distant possibility, agentic coding is already being demonstrated today. For instance, GitHub Copilot can manage entire coding workflows autonomously:

  1. Create a dedicated branch.

  2. Analyze the existing codebase and the reported issue.

  3. Develop and apply a solution.

  4. Test the solution comprehensively.

  5. Generate new unit tests.

  6. Execute all unit tests.

  7. Create a Pull Request (PR).

  8. Validate the implemented fix.

  9. Assign the PR back to a human reviewer.

For developers, this represents a significant shift. For software managers, it introduces both substantial opportunities and challenges. Scrum processes, in particular, will experience significant adaptation as AI becomes integral to software development.

Impacts of Agentic Coding on Scrum Practices:

Scrum Framework Impact Overview:

  1. Product Backlog Refinement

    • AI agents can autonomously break down epics into detailed user stories, write clear acceptance criteria, and estimate efforts based on historical data.

    • Refinement processes become increasingly automated and continuous, potentially reducing lengthy backlog grooming sessions.

  2. Sprint Planning

    • AI agents may suggest clear sprint goals, highlight dependencies, and propose tasks based on past velocities and current resource availability.

    • Human team members will shift from detailed task planning towards prioritizing business value and reviewing agent-driven recommendations.

  3. Daily Scrum

    • Developers spend less time directly coding and more time reviewing, validating, and coordinating the work produced by AI agents.

    • Daily stand-ups transition towards status updates on agent-generated work, such as: "What did my agent complete yesterday? What's currently being processed? What do I need to review?"

  4. Sprint Execution

    • AI agents significantly accelerate coding and testing processes, allowing developers to oversee multiple parallel agent workflows.

    • Human roles shift toward quality assurance, code review, integration, and ensuring alignment with business logic and objectives.

  5. Sprint Review

    • Higher output leads to richer feature demonstrations and deeper stakeholder engagement.

    • Focus shifts from simply showing completed work towards discussions about feature relevance, user value, and overall quality.

  6. Sprint Retrospective

    • Retrospectives increasingly focus on AI performance metrics, addressing agent accuracy, reliability, training effectiveness, and systematic errors or biases.

    • Teams evaluate AI-driven outputs, refining prompts and contexts to improve future agent performance.

Scrum Roles Evolution:

  • Product Owner: Emphasizes defining strategic intent and collaborates with AI tools for backlog refinement rather than manual story detailing.

  • Scrum Master: Facilitates coordination between human team members and AI-generated productivity, managing new challenges such as agent reliability and prompt effectiveness.

  • Developers: Transition to supervising AI-generated code, validating quality, ensuring integration with business logic, and less direct coding.

Artifact Transformation:

  • Product Backlog: AI-generated and refined backlog items become commonplace, automating much of backlog maintenance.

  • Sprint Backlog: Dynamic, real-time task generation and updates based on AI agent outputs.

  • Increment: Increased frequency and volume of code increments necessitate enhanced review processes and quality control measures.

Process Shifts:

  • Reduced Cycle Times: Features and bug fixes delivered at significantly faster rates.

  • Enhanced Automation: Routine tasks such as testing, documentation, and refactoring are largely automated.

  • Emerging Roles: New specialized roles like AI Prompters, Agent Supervisors, and Context Engineers complement traditional Scrum roles.

Conclusion:

While agentic coding will not render Scrum obsolete, it demands evolution. Scrum's foundational principles—transparency, inspection, and adaptation—become increasingly critical as AI-driven development becomes standard. Teams that proactively adapt their processes to leverage AI capabilities effectively will gain considerable competitive advantages.

Given over 30 years of experience using Scrum methodologies and advocating AI adoption, the changes presented by agentic coding are significant and transformative for the software development profession. How do you perceive these changes impacting your Scrum processes and practices?

Comments

Post a Comment

Popular posts from this blog

Yes, Blazor Server can scale!

Image
From the very beginning of the release of Blazor Server naysayers have incorrectly stated that Blazor Server can not scale.  They usually state that the limit is 5,000 concurrent users. There are several misconceptions and wrong assumptions about their statement.  Let's break it down and get a better understanding of Blazor server-side scaling. What is the "limit" for users When Microsoft talks about the need to scale an application, what they are saying is that when a normal response for any concurrent user is taking longer than 200 ms, the system is not performant and needs to scale. We will accept that definition: If any normal user response is taking longer than 200 ms, the system needs to scale for concurrent users. By a normal response, we are referring to a page get, a post, etc.  Large database access requests would not be included in this measurement. What is scaling There are 2 common ways to scale, scale, out horizontally, and scale-up, up vertically. In our di...
Read more

Blazor - Displaying an Image

I wanted to be able to display an image file within a Blazor page.  During my research I realized that there is very little difference between displaying an image in Blazor as compared to displaying it in a HTML page.  So, I decided to add a couple of other features to my application.   The features I have added are:   1. Get a list of files on the server   2. Display at list in a Blazor page   3. Provide a UI effect to zoom in on the image   I will be using the Blazor Server configuration for this application.  We can do this with the Client-side configuration, but you need an API to access the server files.  I have created a folder under WWWROOT called DsiplayImages where I have placed several images I will be working with.  I have created a service that will access the image files from the server.  In addition, I have created a model for the file properties I a need.   ...
Read more

Offline-First Strategy with Blazor PWAs: A Complete Guide 🚀

Image
One of the most powerful features of Progressive Web Apps (PWAs) is their ability to function seamlessly even when offline. For users, this means uninterrupted access to critical features regardless of network conditions. For developers, adopting an offline-first strategy ensures a robust, user-friendly experience while aligning with modern web development best practices. Blazor, Microsoft’s modern web framework, simplifies building PWAs with offline capabilities by leveraging features like service workers, caching, and IndexedDB. In this guide, we’ll dive into how you can implement an offline-first strategy in your Blazor PWA. Why Offline-First Matters An offline-first strategy doesn’t just improve user experience—it also provides: Reliability : Apps remain functional even with intermittent or no connectivity. Performance : Cached assets load faster, improving responsiveness. Engagement : Users can interact with the app at any time, enhancing retention and trust. Key Components of Of...
Read more