863 original articles by Dr. Hernani Costa, PhD, on AI strategy, EU AI Act compliance, governance, and agentic systems for European businesses. Published under CC BY 4.0 — free to read, cite, adapt, and redistribute with attribution.
Claude Code now runs across your terminal, desktop app, phone, and browser, and sessions stay in sync across all of them. If you have been managing multiple Claude Code sessions by switching terminal tabs and losing track of which agent is doing what, there are three features…
Evaluate MCP servers across eight dimensions and a 30-day approval workflow to meet EU AI Act and DORA enterprise governance needs.
Local-first AI does not equal private; map data flows, logs, and reversibility before EU AI Act and GDPR documentation obligations fire.
Learn how to map data flows in a local-first AI assistant to meet GDPR Article 30 and EU AI Act requirements with a 10-boundary framework.
European scale-ups can turn reusable skills, governed memory, and audited harnesses into a compliance layer for EU AI Act and DORA.
Tier your open-source maintainer health rubric by dependency blast radius and replaceability to meet EU AI Act and DORA conformity expectations.
A concrete 30-day pilot runbook to evaluate an open-source AI coding agent before procurement, with seven evidence dimensions and EU AI Act context.
Automate a maintainer health rubric in CI to evaluate open-source AI tools before adoption, ensuring compliance with EU AI Act and DORA.
GitHub stars measure attention, not procurement fitness. Replace them with a license, maintenance, security, and pilot evidence frame.
Kimi 2.6 is a bounded, auditable AI engineering reviewer, not a chatbot replacement. Here is where it fits and where it does not.
CTOs and platform leaders discover why maintainer health outranks star counts for enterprise when selecting open source AI tools.
A decision framework for European engineering leaders to evaluate open-source AI repos by license, maintenance, and data governance.
A practical security checklist for European scale-ups evaluating open-source AI tools before procurement, covering license through DORA.
Learn to split your AI stack into a premium reasoning lane and a low-cost execution lane. Practical guide for European scale-ups.
Local-first AI assistants run on your hardware, never send data to the cloud, and solve compliance. Here is when they make sense for enterprise teams.
The open-source AI tooling boom is real, but winning companies evaluate repos by governance, not star count. Here is what to watch and what to avoid.
Rust is replacing Python and JavaScript in high-performance AI developer tools. Here is why engineering leaders should care, and where to start.
Coding agents are splitting into terminal-native and workflow-native camps. Here is how to choose the right paradigm for your engineering team.
YAML works for simple files, but enterprise teams need validation and reuse. Here is when Pkl makes sense, and how to migrate safely.
AGENTS.md and CLAUDE.md outperform vector databases on the metrics that matter: reviewable, reversible, auditable, and free. Here is how to build them.
/index.json — catalog of all 863 articles with metadata/feed.xml — Atom feed of the 50 most-recent articles/feed.json — JSON Feed 1.1 of the 50 most-recent articles/llms.txt — LLM discovery summary/llms-full.txt — full-text corpus for bulk LLM ingestion (863 articles, ~7 MB)/llms-recent.txt — rolling 30-day window for small-context LLM ingestion/sitemap.xml — XML sitemap pointing to canonical article URLs/hernanicosta.json — Schema.org Person entity for the author