Since writing software was expensive, one of the basic principles of software engineering has been to reuse code whenever possible. If someone had already implemented and debugged something, it usually made more sense to reuse it than to build it again.
Imagine inheriting a 50,000 line legacy application with poor architecture, obsolete libraries, duplicated code, and little documentation. Traditionally, you would either keep modifying the mess or undertake an expensive and risky rewrite.
With AI coding agents, there is a third option.
You can ask AI to analyze the existing software and extract its requirements, behavior, architecture, edge cases, and tests. You can then create a new specification that combines the useful behavior of the old system with new functionality and quality requirements, and have AI implement a completely new version. In other words:
Legacy code → specification → new implementation
rather than:
Legacy code → more legacy code
The valuable asset is not the millions of lines of code accumulated over the years, but the functionality, domain knowledge, assumptions, and tests hidden inside them.
