by | June 1, 2026
In this post, John shows how the first implementation wave in Zeus Academia forced a shift from code-only verification to durable schema enforcement, migration-centric evidence, and more explicit multi-agent handoffs.
by | April 23, 2026
Planning without execution guidance leaves AI agents guessing. In Part 7 of this series, John Miller completes the planning phase for Zeus Academia by creating implementation prompts that translate architectural intent into disciplined, slice-by-slice coding instructions. Learn how execution plans, agent role definitions, and structured prompt templates give both AI tools and human contributors a shared delivery contract — and set the stage for real implementation work to begin.
by | March 31, 2026
Turning architecture into working software requires more than good intentions — it requires a plan. In Part 6 of the AI-Assisted Greenfield Software Development series, John Miller teaches how to use meta-prompts and AI agents to generate the planning artifacts that make vertical-slice delivery predictable: custom-agent governance standards, product requirements documents (PRDs), workflow models, and dependency diagrams. The result is a structured, repeatable handoff from architectural decisions into implementation-ready slices.
| 2/27/2026
In Part 5 of his series on AI-assisted greenfield software development, John delves into the creation of technology-specific instruction files that act as guardrails for AI agents generating code. These files ensure consistency, correctness, and alignment with architectural standards by explicitly defining coding conventions, implementation patterns, testing expectations, and compliance requirements for each technology in the stack. Using AI-generated prompts, John demonstrates how to systematically create instruction files tailored to technologies like Vue 3, ASP.NET Core, MediatR, FluentValidation, Pinia, and more, while maintaining coherence with the project’s overall architectural vision. He emphasizes the importance of keeping project documentation up-to-date and validating governance rules to prevent conflicts in AI-driven workflows. This approach provides a scalable, repeatable framework for leveraging AI in software development, enabling teams to deliver high-quality solutions efficiently.
| 2/2/2026
In this fourth installment of the AI-assisted greenfield development series, learn how to create architecture-level instruction files that guide AI agents in generating consistent, pattern-compliant code. This post focuses on implementing CQRS with event sourcing, demonstrating how to build prompt files that generate comprehensive architectural instructions for MediatR, EventStoreDB, and C# implementations.
| 12/30/2025
In the third post of his series, John Miller explains how he creates instruction files that guide AI code generation. The key is being specific with prompts and tracking code sources to avoid messy output. John covers three instruction files: one for AI code quality standards, one mapping the human-AI workflow with review stages, and one defining a Git workflow for fast updates. He uses prompts to automatically generate and maintain these instructions, making the system flexible. The goal is making AI a reliable team member that speeds up development without breaking things or creating compliance issues.
| 12/1/2025
John writes that AI-assisted coding continues programming's evolution from machine code to high-level languages, rather than revolutionizing it. The core challenge of bridging human intent and machine action remains constant. AI enables natural-language development and better collaboration, but developers are still essential for architecture, safety, and ethics. AI is a tool, not a replacement.
| 9/24/2025
In this post, John Miller outlines a practical framework for AI‑assisted greenfield development that codifies how prompts, instruction files, and chat‑mode configurations work together to produce auditable, reusable code and documentation; he provides concrete templates (for AI provenance metadata, instruction/prompt/chatmode files, and a context‑validation prompt), a canonical chat workflow, and CI enforcement checks to ensure traceability, consistency, and quality of AI‑generated artifacts. John's guidance focuses on embedding standardized metadata, logging conversations and summaries, automating scaffolding, and using token‑efficient instruction patterns so teams can safely scale AI assistance while preserving compliance, reviewability, and continuous improvement across projects.
| 9/21/2025
John Miller introduces a series exploring incremental solution development with AI assistance, specifically GitHub Copilot. This post focuses on establishing business requirements for an academic system by leveraging Object Role Modeling (ORM), a methodology that ensures conceptual clarity, flexibility, and effective collaboration between technical and non-technical stakeholders. Miller highlights ORM’s ability to articulate business rules, detect modeling errors, and enforce data quality, thereby providing robust context for AI-driven implementations. He presents the academic system’s conceptual model, structured workflows, and critical business constraints—such as exclusion and irreflexive ring constraints—to inform solution design while ensuring compliance with rules. John says later posts will detail architecture, tech stack, and iterative AI-guided development.
| 8/30/2025
John addresses the practical challenge of streamlining shared coding standards and best practices using GitHub Copilot across multiple development projects. He explores how developers can avoid duplicating instruction files in each project repository by leveraging symlinks on Linux/macOS and NTFS junction points on Windows. By centralizing shared instruction files in a dedicated GitHub Copilot repository and creating scripts to automate the linking process, John provides a robust cross-platform solution that ensures consistency while minimizing maintenance overhead. The post includes technical details about symlinks and junctions, along with step-by-step scripts for creating these links, ensuring version control hygiene, and customizing for different operating systems. This approach not only simplifies collaboration but also helps teams maintain a single source of truth for shared instructions, making it an invaluable resource for managers, developers, and decision-makers in software projects.
| 7/30/2025
John Miller discusses the various chat modes available in GitHub Copilot, including Ask, Edit, Agent, and Custom modes, emphasizing their distinct functionalities and use cases. He highlights how these modes can streamline coding and automation tasks in developers' workflows by providing contextual guidance, code editing, autonomous task execution, and persona-based AI behavior. Miller also delves into custom chat modes, explaining how users can create tailored configurations to instruct Copilot on specific tasks, thereby promoting consistency and efficiency across teams. Additionally, the post addresses the cost implications of using different modes, particularly noting that while Ask and Edit modes are more cost-efficient with standard models, Agent mode incurs higher costs due to its premium quota demands.
| 5/29/2025
In this final installment of this series on AI-assisted user interface development, John M. Miller demonstrates how GitHub Copilot can efficiently implement client-side sorting in a data table using Vue.js. By providing specific prompts, Miller shows how Copilot can automate complex UI changes like adding sortable columns, which traditionally require multiple code and style updates for interactivity and user feedback. GitHub Copilot outlines a step-by-step approach to enhance table functionality, including adding state variables, computed properties, sorting logic, and UI indicators. To encourage better practices, John prompts GitHub Copilot to change its output into a reusable component of sortable table headers, encouraging modular design and reusability.
| 4/30/2025
In "Developing User Interfaces with GitHub Copilot, Part 3," John Miller illustrates the process of integrating data visualizations into web pages using AI tools. His post focuses on leveraging GitHub Copilot to initially implement a CSS-based Sales Funnel visualization in a Vue.js component, which provides interactive features and visual appeal through hover effects and gradient backgrounds. John then has AI transition the visualization to a chart.js-based implementation, highlighting the library's capabilities in rendering responsive charts with enhanced interactivity and flexibility. John notes this effort didn't need manual coding.
| 3/29/2025
In his second installment on using GitHub Copilot for user interface development, John delves into creating reusable components, specifically an `OwnerSelectDropdown`, to enhance consistency across multiple Vue views. By leveraging Copilot's new multi-file Copilot Edits feature, developers can apply AI-driven suggestions to streamline workflows for large-scale refactoring, such as encapsulating dropdown logic into components and ensuring these updates reflect across related files. John demonstrates the creation and integration of this component into various views, illustrating both the process and challenges involved. He addresses potential errors and emphasizes the iterative nature of refining AI-generated code with strategic prompts, highlighting Copilot's capability to handle syntax but underscoring the necessity that a coder must review the generated code.
| 2/24/2025
In his blog series, John Miller delves into the practical application of GitHub Copilot for developing and modifying user interfaces, using Vue.js as a demonstration framework. This initial post focuses specifically on integrating a new control—a dropdown component—into an existing Vue.js application used for lead management. John illustrates the process of modifying a component to enable the selection of individual lead owners and fetching corresponding data, demonstrating detailed steps on incorporating AI-driven suggestions into coding practices. John emphasizes the importance of providing GitHub Copilot with precise prompts to generate effective code and highlights the role of developers in directing AI through clear instructions and context.
| 1/30/2025
John Miller explores the challenges and benefits of refactoring legacy code by integrating dependency injection (DI) to improve software maintainability and testability. He addresses common issues in legacy systems, such as tight coupling and lack of interfaces, which hinder the ability to conduct effective unit testing. John emphasizes the importance of DI and interfaces in creating flexible, modular, and isolated code components, thereby facilitating easier testing and maintenance. Using a practical example, he illustrates how DI can decouple service classes from specific implementations and discusses the role of tools like GitHub Copilot in automating and accelerating the refactoring process. By implementing DI, developers can enhance code flexibility, allowing for seamless integration of alternative components and improving overall software quality.
| 12/13/2024
John's blog post "Test Generation Using GitHub Copilot," explores the strategic advantages of employing AI, specifically GitHub Copilot, for generating test automation in software development. Acknowledging the risks of integrating AI-generated code in production environments, John suggests that test automation provides a safer entry point due to its non-production deployment. Highlighting test automation's role in exposing design flaws and enabling refactoring, the post demonstrates how Copilot can effectively generate unit tests, using a complex C# BankAccount class as a case study. John goes on to show examples of the process of generating tests using Copilot’s integration with various IDEs, emphasizing that despite occasional test adjustment requirements, AI-enhanced test automation facilitates higher code coverage, efficiency, and reliability. John advocates for embracing AI tools like Copilot to enhance the development workflow, paving the way for more robust and maintainable software systems.
| 11/11/2024
John Miller explores the transformative potential of GitHub Copilot, an AI-powered coding assistant created by GitHub and OpenAI. Leveraging machine learning on vast amounts of public code, Copilot offers context-aware code suggestions, enhancing productivity for developers by streamlining tasks such as writing functions or debugging. John provides a guide to integrating GitHub Copilot with Visual Studio Code, covering installation, authentication, and features like autocomplete, context-aware coding, multiline completions, and example-based learning. He delves into the functionality of the @workspace command, Copilot's chat commands, and various integration features within VS Code. The post emphasizes Copilot's ability to optimize the coding process, allowing developers to focus on creative problem-solving by reducing the burden of writing boilerplate code and improving overall workflow efficiency.
| 10/14/2024
John Miller explores how AI is transforming the tech industry by enhancing developers' capabilities rather than threatening their jobs. He emphasizes that developers who embrace AI can automate repetitive tasks, enhance coding efficiency, and focus on more strategic work. Key insights from McKinsey and Microsoft highlight AI's role in accelerating code documentation, optimization, and writing, while also promoting deep work by minimizing interruptions. Improved developer experiences lead to higher product quality and employee satisfaction. John advocates for adopting an AI mindset to maintain a competitive edge and plans to delve deeper into AI's impact on the software development life cycle in future posts.