Blog
Notes on AI engineering
Practical articles on AI agents, RAG, LLM integrations, evals and security — from real projects, no fluff.
AI coding assistants in a dev team: an adoption playbook that survives contact with reality
How to roll out Claude Code, Copilot, Cursor and similar tools across an engineering team: what the research says about productivity, which policies you need, and how to measure the impact honestly.
LLM cost optimization: prompt caching, batching and choosing the right model
How to cut LLM API costs without losing quality: prompt caching, batch processing, effort settings, model routing and token hygiene, with real price math.
EU AI Act for software companies: what applies in 2026 and what to do now
EU AI Act timeline after the 2026 Digital Omnibus, risk categories, provider vs deployer duties, Article 50 transparency and a practical compliance checklist.
AI agent security: prompt injection and the OWASP Top 10 for LLMs
How prompt injection works, what the OWASP Top 10 for LLM applications covers, and the architecture patterns that keep AI agents with tools and data safe.
How to evaluate LLM applications: building evals that catch regressions
A practical guide to LLM evals: golden datasets, code-based checks, LLM-as-a-judge, regression testing in CI and the metrics that actually predict user satisfaction.