Petri: An open-source auditing tool to accelerate AI safety research \ Anthropic

A new automated auditing tool for AI safety research

Alignment Petri: An open-source auditing tool to accelerate AI safety research Oct 6, 2025 Read the technical report Petri (Parallel Exploration Tool for Risky Interactions) is our new open-source tool that enables researchers to explore hypotheses about model behavior with ease. Petri deploys an automated agent to test a target AI system through diverse multi-turn conversations involving simulated users and tools; Petri then scores and summarizes the target’s behavior. This automation handles a significant part of the work that one needs to do to build a broad understanding of a new model, an

related reading

• Petri: An open-source auditing tool to accelerate AI safety researchalignment.anthropic.com
• Petri 2.0: New Scenarios, New Model Comparisons, and Improved Eval-Awareness Mitigationsalignment.anthropic.com
• Claude Mythos Preview System Cardwww-cdn.anthropic.com
• AuditBenchalignment.anthropic.com
• [2602.22755] AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviorsarxiv.org
• Security incident disclosure — July 2026huggingface.co
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Introducing Bloom: an open source tool for automated behavioral evaluations \ Anthropicanthropic.com
• [2602.22755] AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviorsarxiv.org
• Building and evaluating alignment auditing agents — AI Alignment Forumalignmentforum.org
• A “diff” tool for AI: Finding behavioral differences in new models \ Anthropicanthropic.com
• Building and evaluating alignment auditing agentsalignment.anthropic.com