Martin Fowler backs letting AI debugging agents read the code last, not first

On his site Oct. 21, software author Martin Fowler recommended an essay by Cindy Sridharan on debugging with AI agents. Her view, which he summarized approvingly, is that an agent should first gather evidence about how the system behaves and only then form hypotheses from the code. Fowler noted that a human is still needed to steer the agent.

Photo: Paris Buttfield-Addison / Wikimedia Commons, CC BY 2.0 (cropped)

Sources

• In their own words Martin Fowler（Thoughtworks） (2026-10-21)
  Fragments: October 21

Editorial policy ・ Terms of use