Security and Safety

Audit Logging

Audit logging creates a tamper-resistant record of every action an agent takes, including tool calls, file modifications, API requests, data access, and decision points, giving you the forensic trail needed for security investigations, compliance audits, and post-incident analysis. Unlike standard application logging, agent audit logs must capture the full reasoning context: not just what the agent did, but what information it had access to and what triggered each decision, because agent behavior is non-deterministic and you cannot reproduce an incident by simply re-running the same input. Organizations evaluating agentic coding tools for enterprise use treat audit logging as a prerequisite rather than a nice-to-have, because without it you cannot prove accountability for AI-initiated changes to regulators, auditors, or your own security team.