Posts about Artificial intelligence

How to use AI skills to capture conventions, architecture, and internal patterns of a team. Not magic, but operational documentation.

What changes when an AI demo becomes a real product: logs, costs, evaluation, permissions, fallback and maintenance.

Critical analysis of permissions, scope, auditing, and limits when connecting AI agents to real systems with MCP.

How to integrate an LLM into a real backend: layered architecture, provider abstraction, limits, errors, costs, and tests.

Learn the differences between MCP and skills in AI: what each one does, when to use them, security risks, and how to apply them responsibly in companies.