ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures

Widespread deployment of AI agents in software engineering is surfacing a long tail of rare but highly dangerous misalignment bugs. Since sampling this behavior is intractable, we decompose these failures into three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it; and agent harness errors, where the safe action fails to execute. Across 8 evaluations that stress test these mechanisms, we find that frontier models are difficult to steer, elicit dangerous behavior through just 3 conditioning examples, and can randomly generate destructive commands at nontrivial probabilities. These three mechanisms naturally lend to targeted mitigations for each one, inspiring our harness modification ClayBuddy. ClayBuddy allows the agent to modify its own harness to provide safety guarantees, including a novel tool to selectively truncate its own context. We measure ClayBuddy's efficacy across safety and capabilities, finding that it eliminates violations across some tasks. This demonstrates that our decomposition is effective and is an example of our harness design philosophy.