Notes on AI and DevSecOps
I am Alessandro Nigro, a freelance Senior Software Engineer in Milan and an IT consultant since 2009. These notes cover the work I do every day: AI agents and LLMs in production, retrieval over company documents, DevSecOps and the security of software written with AI. Each note links the official sources I used.
AI Agents in Production: What It Takes Beyond the Prototype
What an LLM agent needs to survive real users: evals, narrow tools, cost limits, logs, injection defenses and a way back to a human.
Updated
Enterprise RAG: Where It Actually Breaks
The four places where a RAG system over company documents gives wrong answers, and how I evaluate it before it reaches users.
Updated
DevSecOps for AI-Written Apps: What to Check Before Launch
The checklist I run before an app written with AI assistants goes live: secrets, hallucinated packages, access control, cloud permissions, pipeline.
Updated
What Is DevSecOps, and How a Real Company Does It
DevSecOps defined from the official sources, then how it works in practice: pipeline checks, secrets, dependencies, cloud permissions and who owns what.
Updated
AI for Software Development: What I Actually Use
How I work every day with a coding agent, what independent studies say about productivity, and where a person still has to decide.
Updated