Taylor Luttrell-Williams and Killian Carlsen-Phelan introduce Gitar, Sonar’s AI code reviewCode review examines proposed source changes to assess their correctness, clarity and suitability before or around integration. tool, and walk through a sample ticketing application with three pull requests. The presenters frame the workshop around reviewing code produced at high volume by coding agentsAn AI coding agent is a tool-using AI system that can inspect, modify, and validate software within a repository..
The first example shows a review finding a ticket-transfer bug outside the changed lines. A second uses repository-specific rulesContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task. to check a business requirement that customer-facing prices include fees.
The third demonstrates investigating a failed CI testDebugging is the process of finding why software behaved incorrectly and checking that a correction addresses the cause. and enabling automatic fixes and mergingWorkflow automation uses software or AI to complete a connected sequence of routine steps with less manual effort.. These are vendor demonstrations rather than independent proof that an automated reviewer catches every issue; teams remain responsible for their own safeguards and review choices.
Watch on YouTube
