AI agents are getting more complex. Developers shouldn't have to babysit them.

AI coding agents are becoming more autonomous, thanks to advances in harness engineering that enable them to identify and correct mistakes before human review. In the latest episode of The New Stack podcast, Vanitha Kumar, Marketing Technology Director and Technical Partner at Thoughtworks, explains how automated tests, feedback loops, and guardrails allow agents to handle longer running tasks with less human intervention while working in parallel.