Content by hidde de smet (22)

Hidde de Smet shows how to add fast local guardrails for Azure Terraform by running fmt, validate, tflint, Trivy, and terraform-docs on every git commit. The post includes a working pre-commit config, Azure-specific lint rules, and an MCP-based workflow to keep generated HCL current and policy-aligned.

Hidde de Smet compares the GitHub Copilot App and the VS Code Agents Window, focusing on how each surface supports agent-first workflows: isolated sessions, worktrees, review/CI loops, and customization via MCP and instruction files. It includes a practical “which one should you use?” decision guide for day-to-day development vs delegated work.

Hidde de Smet lays out a practical KPI scorecard for teams adopting AI coding agents under usage-based billing, using GitHub Copilot’s AI Credits model as the concrete example. It focuses on measuring speed, quality, reliability, and spend together, with a rollout plan and data sources you can wire into a weekly dashboard.

Hidde de Smet compares GitHub’s Spec-Kit and Fission AI’s OpenSpec for spec-driven development, focusing on how each tool structures specs, guides agent workflows, and fits greenfield vs brownfield work.

Hidde de Smet breaks down what AI coding agents actually cost once GitHub Copilot switches to usage-based billing, including how credits map to tokens, why model choice changes your bill, and how to budget for agent-heavy teams without surprising finance.

Hidde de Smet shows how to combine five GitHub Copilot customization file types in a single .NET Aspire repo, so the right instructions, skills, prompts, and agent roles load at the right time without bloating every chat request.

Hidde de Smet compares three AI coding setups—single-agent, agent-with-tools, and multi-agent—using a realistic .NET Aspire + ASP.NET Core rate-limiting task to show trade-offs in fit, cost, latency, and common failure modes.

Hidde de Smet explains how Spec-Kit’s extension system works, highlights useful community extensions, and walks through the Ralph Loop extension, which runs a GitHub Copilot agent in iterations to implement tasks from `tasks.md`, commit changes, and track context in `progress.md`.

Hidde de Smet explains practical frameworks and real-world techniques for effective prompt engineering and context engineering with LLMs and agent tools, including GitHub Copilot, helping AI practitioners move from vague queries to reliable, production-grade results.

Hidde de Smet explains how teams can move from individual AI-powered workflows to collaborative, spec-driven development. Explore practical team setups, CI/CD integrations, and advanced architecture strategies to grow your next Microsoft-focused project.

Hidde de Smet delivers a comprehensive field guide for developers mastering AI-assisted and spec-driven development. This post, Part 3 of his series, dives into debugging, best practices, troubleshooting, and automation for production-ready workflows.

Hidde de Smet continues his AI-assisted development series by demonstrating the full Spec-Kit workflow—detailing how to move from requirements to production-ready code using .NET 9, Blazor, and GitHub Copilot. A must-read for software engineers adopting modern, spec-driven workflows.

Hidde de Smet kicks off a deep-dive series on mastering AI-assisted development, highlighting why uncritical 'vibe coding' falls short and how specification-driven approaches like GitHub’s Spec-Kit help teams achieve robust production code.

Authored by Hidde de Smet, this guide provides a deep dive into the creation and operation of an AI Center of Excellence (CCoE), offering practical frameworks and strategies for coordinated, effective enterprise-wide artificial intelligence adoption.

Hidde de Smet offers an expert comparison of Azure Bicep, Terraform, and OpenTofu for Infrastructure as Code. This comprehensive post supports infrastructure and DevOps professionals in selecting tools for Azure, multi-cloud, and open-source strategies.

In this comprehensive guide, Hidde de Smet documents the step-by-step evolution of Terraform infrastructure for Azure. The post provides real-world insights and actionable patterns for teams modernizing their infrastructure-as-code, from basic setup to advanced automation and governance.

In this concluding article, Hidde de Smet guides readers through defining success metrics, piloting, and essential learnings for effective and responsible AI project implementation.

Hidde de Smet presents Part 2 of his series on validating AI projects. This installment demonstrates practical uses of an AI decision framework and examines essential ethical considerations—such as bias, transparency, and workforce impact—when evaluating AI initiatives.

Hidde de Smet shares Part 1 of a 3-part series on validating AI initiatives, focusing on a decision tree framework that helps organizations determine if AI is the best fit for solving their business problems.

Written by Hidde de Smet, this detailed guide walks readers through each stage of building and deploying an image classification solution using machine learning, covering both conceptual and practical considerations.

Written by Hidde de Smet, this article delves into the Model Context Protocol (MCP), highlighting its design, features, and transformative impact on AI integration for organizations such as Microsoft.

Written by Hidde de Smet, this article explores GitHub Copilot's Agent Mode, highlighting how it transforms the coding workflow by supporting natural conversations, interactive problem-solving, and step-by-step guidance directly within your development environment.