Agentic AI can do more than develop new features: it can continuously improve the existing software. Three autonomous feedback loops show how this can work for correctness, performance and architecture, why the effort AI agents spend on changes could become a new maintainability metric, and why humans still have to set goals, limits and acceptable risks.
A guided rocket doesn’t have to be perfectly aligned at launch, as long as it knows its target and can correct its course. The same applies to AI agents: what moves to the center is the ability to aim at the right targets, check the direction automatically and readjust. Software development offers particularly good conditions for this.
AI software factories come as light factories with a human in the loop and as dark factories without human reviews. A gray software factory works autonomously by default, but decides for every single change, based on an automated risk and quality classification, whether a human needs to be involved.
This website ran for years on a very old JBake fork and has now moved to Hugo: 73 articles in two languages, old URLs, audio, admonitions. Implemented with an AI agent, steered through a Werkbaum. This article describes the process and why Werkbaum proved itself as a planning tool for agentic AI in particular.
SQL and CSS are both declarative languages. Why do many backend developers write complex SQL queries with ease, yet despair over CSS? A comparison of locality, hidden dependencies, and the question of how declarative both languages really are.