Agent Action Audit Trail
Added May 2026
Log every AI agent tool call, decision step, memory read or write, and external interaction. Records must allow reconstruction of the full action sequence.
Objective
Enable after-the-fact accountability and incident investigation for agent-driven workflows (tasks AI systems carry out on their own) by maintaining a complete, tamper-evident action log (changes are detectable).
Maturity Levels
Initial
Agent actions are not logged; only final outputs are available for review.
Developing
Some agent actions are logged but coverage is incomplete and logs are not structured for audit use.
Defined
All tool calls, decision points, and external interactions are logged with timestamps, inputs, outputs, and agent identity.
Managed
Logs are centralized, retained per policy, and queried regularly during incident investigations and governance reviews.
Optimizing
Logs are analyzed automatically for anomaly detection (spotting unusual activity); structured log data feeds the processes used to improve the AI models.
Evidence Requirements
What an auditor or assessor would expect to see for this control.
- —Log schema (format) documentation specifying required fields, storage type (append-only, meaning entries can be added but not changed), access controls, and retention period
- —Sample audit log entries confirming all required fields are present and populated for a representative set of agent workflows
- —Storage integrity configuration evidence confirming write-once, access-controlled storage with no modify or delete access for normal operations
- —Retention compliance report confirming logs are maintained for the required period
- —Cross-agent trace records showing the trace_id being passed from agent to agent for at least one multi-agent workflow
Implementation Notes
Key steps
- Log at the tool boundary (where the agent calls an outside system), not just the AI's response: capture the exact call, the inputs sent, and the raw response. The AI's own summaries of tool results are unreliable.
- Include a session/trace ID (a shared reference number) that links all steps in a single agent workflow, enabling full reconstruction of multi-step sequences.
- Treat agent logs with the same integrity requirements as financial audit logs: write-once (entries cannot be edited once recorded), tamper-evident storage, access-controlled.
- For multi-agent systems (several AI agents working together), carry the original trace ID from agent to agent so shared workflows can be traced end-to-end.
Example Implementation
Finance team using an AI agent to prepare and submit regulatory filings
Agent Audit Log Schema: Regulatory Filing Agent
Required fields per log entry:
| Field | Type | Description |
|---|---|---|
| trace_id | UUID | Links all steps in one filing workflow |
| step_seq | Integer | Step number within trace |
| agent_id | String | Agent version identifier |
| tool_name | String | Exact tool or API called |
| tool_input | JSON | Full parameters passed (PII hashed) |
| tool_output_hash | SHA-256 | Hash of raw tool response |
| tool_output_summary | String | Non-sensitive summary for review |
| timestamp | ISO-8601 | UTC timestamp of tool execution |
| outcome | Enum | SUCCESS / ERROR / REJECTED |
Storage: Append-only log store; no delete or modify access except to designated retention manager after documented hold period
Retention: 10 years (EU AI Act Art. 12 high-risk logging requirement)
Cross-agent: trace_id propagated to any sub-agent invocations to enable end-to-end reconstruction