AI-Assisted Greenfield Software Development, Part 7: Implementation Prompts

John Miller | 4/23/2026

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.

AI-Assisted Greenfield Software Development, Part 6: Vertical Slices and Implementation Planning

John Miller | 3/31/2026

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.

Cloud Data Transformation in Fabric with Medallion Architecture

Ginger Grant | 2/27/2026

Ginger explores how medallion architecture addresses the limitations of legacy ETL (Extract, Transform, Load) processes to meet the demands of modern data science, AI, and analytical workloads. She highlights the brittleness of traditional ETL pipelines, which often resulted in lost data, poor governance, and untestable transformations, and contrasts this with the multi-layered medallion approach. The architecture organizes data into bronze (raw data), silver (validated and transformed data), and gold (analysis-ready data) layers, ensuring robust governance, scalability, and trustworthiness. Grant emphasizes the importance of testing processes, securing sensitive data, and collaborating with stakeholders to meet organizational needs.

AI-Assisted Greenfield Software Development, Part 5: Technology Guardrails

John Miller | 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.

Tool Installation Guide

This post provides a comprehensive guide for preparing tools required for CODE Training's AI-assisted Software Development class. You'll find step-by-step instructions for installing and setting up essential software, including GitHub, Visual Studio Code, the GitHub Copilot extension, GitHub Copilot CLI, and the Mob.sh mob programming tool, on both Windows and macOS platforms. CODE suggests that you have a GitHub account, preferably with a paid Copilot license, but free models can be used. Enjoy the class.

Do I Need a Database Anymore?

Ginger Grant | 2/2/2026

Are traditional databases necessary in 2026? Advances in storage compression, memory interfaces, and AI-powered retrieval have reduced reliance on costly databases that require extensive maintenance and tuning. Microsoft Fabric offers a transformative alternative, providing four flexible storage options that handle massive datasets using open-source Parquet files at lower costs than traditional cloud databases. Maybe your organization should consider adopting Fabric for future-ready, cost-effective data infrastructure.

AI-Assisted Greenfield Software Development, Part 4: Architecture Prompts and Instructions

John Miller | 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.

AI Assisted Greenfield Software Development, Part 3: Generating the Process Instruction Files

John Miller | 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.

What Happened to Power BI?

Ginger Grant | 12/29/2025

Ginger Grant explains that Power BI remains a healthy, actively developed product despite recent licensing changes and Microsoft's emphasis on Fabric; you can still use Power BI standalone, but Fabric provides compelling benefits for organizations that need scale, real‑time performance, and more modular development. By moving data engineering, security, and storage into Fabric’s OneLake and using features like Direct Lake, teams gain near‑instant, scalable reporting, better pipeline and notebook workflows, improved monitoring and validation, and easier collaboration than traditional Power Query approaches. In short, Fabric is not required, but it materially enhances Power BI for enterprise scenarios.

What's the Big Deal?

John Miller | 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.

Microsoft Fabric: The New Method for Organizing Data in the Azure Cloud

Ginger Grant | 11/1/2025

Ginger Grant presents Microsoft Fabric as a unified, modern solution for organizing and centralizing organizational data in the Azure cloud (and beyond) with dramatically simplified setup and governance. She explains how Fabric replaces the traditional mix of disparate tools (Data Factory, Databricks, Data Lake, IoT/Event hubs, and databases) with a single, configurable resource that orchestrates data from multiple sources—including multi-cloud and Snowflake—through seamless referencing or mirroring rather than heavy data import. Fabric includes broad tool compatibility (PySpark, T-SQL, Power Query, notebooks) and a predictable fixed-hourly pricing model, plus a centralized storage layer called OneLake. Overall, Fabric addresses complexity, cost, and collaboration challenges by delivering an integrated, cross-provider data platform.

Self-Service Reporting: Setting Up Successful Reporting for Everyone

Ginger Grant | 10/7/2025

Ginger makes the case for giving business users the tools to create their own reports. When IT controls all data access, teams often resort to inefficient workarounds that create security risks and waste time. She shows how Microsoft Fabric and Power BI can solve this problem by giving users secure, well-governed access to the data they need. With the right setup, people can build their own reports without sacrificing data quality or creating chaos. The result? Less waiting on IT, more consistent data across the organization, and faster, smarter decisions.

AI-Assisted Greenfield Software Development, Part 2: Core Instructions

John Miller | 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.

AI-Assisted Greenfield Software Development, Part 1: Business Requirements

John Miller | 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.

Sharing Instructions with the Team

John Miller | 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.

The Strategic Case of Open-Source Data Engineering

Ginger Grant | 8/29/2025

Ginger explores how companies can break free from the expensive 10-year cycle of proprietary data transformation tools by embracing open-source technologies like Python and Spark, which Microsoft Fabric now fully supports through its adoption of vendor-agnostic approaches and Medallion Architecture.

When Database Alternatives Make Business Sense: A Microsoft Fabric Perspective

Ginger Grant | 7/31/2025

Ginger Grant examines the transition from traditional databases to Microsoft Fabric's analytics-focused architecture. Fabric uses Delta Parquet files in scalable lakehouses and warehouses, supporting familiar tools like T-SQL and Power BI while adding AI-powered natural language queries. While databases excel at fast transactions, Fabric offers cost-effective, petabyte-scale analytics with integrated AI tools, making it ideal for organizations prioritizing data analysis over transactional processing.

Modes of Chatting with GitHub Copilot

John Miller | 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.

Turning Data into Information with Fabric

Ginger Grant | 7/2/2025

Microsoft Fabric addresses the challenge of data silos by creating OneLake, a unified data lake that consolidates organizational data from multiple applications like CRMs, HR systems, and accounting software. The platform transforms fragmented data into actionable information through shortcuts, real-time database mirroring, and integrated analytics tools. By combining lakehouse and warehouse structures with security controls, Fabric enables organizations to achieve a single version of truth for data-driven decision making across Power BI, Excel, and other Microsoft tools.

Unlocking the Promise of Data-Driven Decisions: Why Microsoft Fabric Can Succeed Where Legacy Systems Failed

Ginger Grant | 5/30/2025

Ginger Grant examines the challenges organizations face in transforming data into data-driven decision-making. Despite the pervasive availability of data, many companies have struggled with disjointed systems and inaccurate data, leading to failed AI implementations and ineffective decision-making. Microsoft Fabric, supported by Azure's cloud capabilities, addresses issues inherent in past data solutions, including integration, storage, and visualization, to provide a cohesive approach for data-driven insights. Microsoft Fabric stands out with its open standards, low-code tools, and interoperability with platforms like AWS, Google Big Data, and Snowflake, making it accessible for diverse organizational needs. Ginger thinks Microsoft Fabric is a game-changer that can help companies connect, clean up and organize data, leading to intelligent business decisions through streamlined data processes. Future posts in this series will discuss the business considerations in how to connect the data using Microsoft Fabric to get to data-driven decision-making.

Developing User Interfaces with GitHub Copilot, Part 4

John Miller | 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.

Developing User Interfaces with GitHub Copilot, Part 2

John Miller | 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.