How to meet it
OWASP AISVS v1.01
Monitoring, Logging & Anomaly Detection · Request & Response Logging
Log AI interactions with context
Verify that AI interactions are logged with session context and AI-specific telemetry.
OWASP AISVS v1.01, requirement 12.1.1
In plain English
For every AI call, record enough to reconstruct what happened later: who asked, in which session, which model and version answered, what went in, what came out and what the safety checks decided.
What good looks like
- Each entry has a timestamp, the user or service identity, session and request IDs, the model and version, the input and output, token counts, guardrail decisions and any tool calls.
- Sensitive content is redacted or minimised, in line with your privacy policy.
- Logs go to a central store with access controls and a set retention period.
How teams usually do it
- Log in one gateway or proxy that every model call passes through, so every app logs the same way.
- Use a shared naming scheme for fields, for example the OpenTelemetry conventions for generative AI.
- Send the logs to your security monitoring (SIEM) so they can feed alerts (see 12.2.1).
Evidence an auditor would accept
- Sample log entries.
- The logging configuration, retention period and who can access the logs.
- A walkthrough that reconstructs one real session from the logs.
Common mistakes
- Logging only errors.
- Logging full prompts that contain personal data, with no redaction or retention limit.
- Each team logging in its own format, so events cannot be joined up across systems.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.