Healthy code needs 22 to 35% fewer tokens for agentic code review
A pre-registered study shows what unhealthy code costs AI agents to review. See the numbers and the limits.
Adam Tornhill is a programmer who combines degrees in engineering and psychology. He’s the founder and CTO of CodeScene where he designs tools for code analysis. Adam is also a recognized international speaker and the author of multiple technical books, including the best selling Your Code as a Crime Scene and Software Design X-Rays. Adam’s other interests include modern history, music, retro computing, and martial arts.
A pre-registered study shows what unhealthy code costs AI agents to review. See the numbers and the limits.
A legacy uplift that would traditionally have been a 12–18 month, high-risk engineering project was completed in three weeks of...
How CodeScene’s Code Health and MCP tools turn agentic speed into sustainable engineering practices.
Benchmarks and use cases for agentic refactoring with the CodeScene CodeHealth MCP Server.
In this article, we’ll use a statistical model that translates Code Health scores into tangible business value – faster...
CodeScene surpasses SonarQube by 6 times on the public software maintainability dataset, scoring 83% vs. SonarQube's 13.3% using...
Evolution is a series of articles that explore novel approaches to understanding and improving large-scale codebases.
These days it's probably easier to find a winged unicorn than a software organization who hasn't adopted Agile.