Spec-Driven Development in a Modular Monolith — AI Skills, Context, and Change Verification

From Principles to Practice In our previous article, Spec-Driven Development: How to Delegate Implementation to AI Without Losing Control, we covered the fundamentals: specifications, technical plans, task lists, and the rules and skills that guide and constrain AI models. This time, we'll explore how this approach works in a system that has been developed and maintained for years. AI-generated code must work within an existing architecture, alongside established integrations

Generating an application is not the same as making it safe for a business to depend on. The harder questions begin when a useful prototype needs shared access, approved business data, reliable deployment and an owner who can maintain it. Oracle’s October 27, 2026 App Composer announcement targets that transition. It describes a path from applications built with Codex and other AI tools to deployment on Oracle Cloud Infrastructure, with organizational permissions and access c

An AI-generated prototype can demonstrate an idea. Production software must do something harder: behave correctly, respect access boundaries, survive changes, and remain understandable to the people who maintain it. That gap is the practical focus of Poland’s DevAI by Data Science Summit, scheduled online for October 19, 2026, and in Warsaw on October 20. Its agenda brings repository safety, permission boundaries, verification loops, and production failures into the same conv

Poland’s planned municipal open-source pilots point to a potential market for software agencies: helping local government migrate, integrate and operate open technologies. The immediate signal is concrete but limited. On October 12, 2026, the Ministry of Digital Affairs announced a November 12 event that will give the proposed pilots particular attention. It described the funding competition as the next step, not an already-open application window. For developers and integrat

Event-driven coding agents have moved from demo mode to operational mode, and that shift matters now because it changes where engineering teams get leverage - and where they lose control. Cursor’s August 19, 2026 update introduced cloud agent subscriptions that let agents wake up on pull request activity, Slack thread replies, and schedules. That is a fundamental workflow change: instead of repeatedly re-prompting an agent, teams can let it hold an objective over time and con

Open source risk has changed from "can someone sneak bad code into a package?" to "can attackers scale believable compromise across thousands of packages and pipelines before defenders react?" That shift is exactly why recent npm incidents are so important for engineering leaders right now. The threat is no longer just isolated typosquats. It now blends maintainer compromise, install-time malware execution, CI credential theft, and AI-workflow abuse into one supply-chain kill

Developer teams are rapidly moving from text-only bug reports to visual-first debugging conversations. The July 2026 Copilot updates in VS Code made that shift explicit by adding screenshot and area-screenshot context directly in Copilot Chat, right when agentic browser tooling also became generally available. That combination matters because it changes how teams communicate UI defects, reproduce issues, and decide what an agent should do next. For engineering leaders, this i

AI coding assistants are now part of production software delivery, but GhostApproval shows how quickly convenience can become an enterprise risk when trust boundaries are weak. The July 2026 wave of disclosures landed at exactly the moment many organizations were scaling agentic development workflows, and it exposed a hard truth: approval prompts are not a safety control if they can be tricked into showing the wrong target. GhostApproval matters because it is not only about o

When I first encountered the agile software workflow, I was intrigued by its promise of flexibility and speed. Over time, I’ve seen how this approach transforms projects, making them more adaptive and responsive to change. If you’re curious about why so many teams are adopting this method, you’re in the right place. Let’s explore the key advantages of the agile software workflow and how it can help you build better products. Why the Agile Software Workflow Stands Out The agil

July 30, 2026 is not just a platform update date - it is a forcing function for AI operations teams. With AWS confirming that Amazon Mechanical Turk will stop accepting new customers on that date while keeping existing customers running in a maintenance posture, companies that still depend on open crowd workflows now face a hard architectural decision: patch the old pipeline, or redesign human-in-the-loop systems for modern model development. For engineering leaders, this is

Copilot updates in July 2026 are not just product polish. They are a clear signal that AI coding tools are moving from growth mode to governance mode - where cost controls, policy defaults, and platform consolidation matter as much as model quality. The most important deadline is now fixed: GitHub Models will be fully retired on July 30, 2026. For teams that still depend on its playground, catalog, inference API, or BYOK endpoints, this is no longer a roadmap item. It is an i

AI is entering the codebase without clear rules AI has become part of the daily work of technology teams faster than many organizations have been able to establish a sensible process for using it. A model can generate classes, tests, or parts of a feature within minutes. However, speed alone does not guarantee that the result will support the business objective, respect the existing architecture, or remain within the boundaries of the system. The problem: Vibe Coding In pract