The article explores how advancements in AI coding tools will reshape software engineering in 2026. It highlights shifts in infrastructure, testing practices, and the importance of human oversight as LLMs generate code. The author raises questions about the evolving roles of engineers and the implications for project estimates and build vs. buy decisions.

The article discusses the challenges and realities of estimating software project timelines. It argues that traditional estimation methods often fail due to the unpredictable nature of software development and suggests an approach focused on political context and risk assessment rather than rigid timeframes.