BLOGSEM Devs
Articles on software development, web and technology
Your AI vendor can be switched off by a government you do not vote for
On 12 June a US export-control order switched off a frontier model for everyone, everywhere, for eighteen days. What that means for a European SME with a feature in production, and how you actually defend against it.
The AI Act omnibus is law: what slipped and what starts on 2 August
The Digital Omnibus took effect on 27 July and pushes the high-risk rules out to December 2027. Article 50 did not move: from 2 August 2026 chatbots, generated content and deepfakes must be disclosed, and in Italy ACN does the enforcing.
EU AI Act for SMEs: what kicks in during 2026 and what to do now
The EU AI regulation phases in over time. Many SMEs assume it doesn't touch them. Often it does. Here's what matters if you build AI features.
Coding with AI agents in 2026: how our workflow actually changed
It's no longer autocomplete. Agents read the repo, open PRs, fix tests. But the bottleneck moved, it didn't vanish.
Tailwind CSS v4 in production: is the new engine worth the migration?
The Oxide engine, CSS-first config, faster builds. We migrated three real projects. What we gained and where it hurt.
AI agents for SMEs in mid-2026: what really works and what doesn't
A year after the autonomous-agents season, the operational level has risen. But winning use cases are few and well-defined.
GSD: The Meta-Prompting and Context Engineering System for AI Coding Assistants
Discover how GSD can help you manage context and streamline complex project workflows in software development
How OpenAI Codex Works: A Technical Guide
Discover how OpenAI Codex uses artificial intelligence to generate high-quality code and improve developer productivity
Vercel Marketplace and AI integration: what's nice, what's not
Vercel revamped the Marketplace integrating AI assistants for setup, debug, deploy. What really works.
VS Code built-in AI: do we still need Copilot?
Microsoft built native AI into VS Code. For Copilot subscribers, is it still worth $19/month? Field test.
AI agents in customer operations: 2026's first reckoning
After a year of agents on tickets, lead routing and qualification, we know where they pay off and where they ruin things. Three patterns that work, three that don't.
Dependency security: SBOM, Trivy, Snyk and what we learned
Knowing what's inside your software is now mandatory, not optional. Three tools to start seriously.
Claude 4.5 and prompt caching savings: real numbers in production
Anthropic shipped Claude 4.5 with more efficient prompt caching. For teams running AI assistants in production, savings are real.
AI video generation in business: Sora, Veo, and what's actually useful
Mature AI video models in 2025. For marketing, training or product: where they pay off and where not yet.
WCAG 2.2 AA: real audits on 6 Italian e-commerces, the 7 things always failing
The European Accessibility Act is live. Across six audits, seven recurring issues that block AA.
From NextAuth.js to Auth.js v5: the migration explained
Auth.js v5 went stable. What changes, how to migrate, and why we waited.
