How do I add compliance logging to CrewAI agents?

Use CrewAI's task callback system: add a callback= parameter to each Task constructor. The callback fires after task completion with the task output. In the callback, call ghost.capture() with subject_id (who was affected), decision_type (the task description), context (inputs at decision time), action (task output), and decision_id (shared across all tasks in the crew run). Generate a UUID decision_id before crew.kickoff() and pass it to each callback via closure. Ghost SDK fires asynchronously — under 5ms overhead, no changes to your agent logic.

How do I capture compliance records in CrewAI Flows?

In CrewAI Flows, add ghost.capture() calls inside each @listen method, after the crew or logic that produces the state transition output. You have access to the complete current state (self.state), which provides the context for the capture. Use self.state.decision_id (set in the @start method) as the correlation key across all flow steps. This creates one compliance record per flow state transition, linked by decision_id — enabling full pipeline reconstruction from @start through the final @listen step.

What is the difference between CrewAI task callbacks and step_callback for compliance?

Task callbacks fire once per task completion — coarser granularity but lower volume. The task output is the compliance record action. Best for sequential and hierarchical crews where the task result is the audit-relevant decision. step_callback fires after every individual agent action step including tool calls — finer granularity, higher volume. Best when tool calls have direct real-world effects (database writes, API calls, notifications) and each tool invocation requires an audit record. For most compliance use cases, task callbacks are sufficient; add step_callback specifically for tool-use capture in crews making consequential external actions.

How do I handle multi-crew pipelines with CrewAI for compliance?

Generate a decision_id at the pipeline entry point — before any crew is instantiated — and pass it to each crew's callback closures. When one crew's output feeds into another crew's input, include the decision_id in the handoff context. Each crew's task callbacks use the same decision_id. When a regulator or auditor requests the complete decision trail for a specific case, querying by decision_id returns all task records across all crews in the pipeline in order, from the first crew's initial task through the final crew's concluding task.

CrewAI Compliance: How to Add Audit Logging to Multi-Agent Pipelines

CrewAI's role-based model makes tasks the natural compliance audit boundary — each task has a specific agent role, a defined input, and a captured output. Compliance logging uses three integration points: task callbacks (per task completion, for sequential and hierarchical crews), step_callback (per agent action step including tool calls), and @listen decorators (for Flows state transitions). A shared decision_id generated at crew entry links all tasks in a pipeline run. Ghost SDK's fire-and-forget capture() call adds under 5ms overhead and no changes to agent logic.

Task Callbacks for Sequential Crews

The simplest CrewAI compliance integration: add a callback= parameter to each Task constructor. The callback fires after task completion with the task output. The compliance callback extracts subject_id (passed via closure), decision_type (matching the task description), context (the inputs at decision time), action (the task output), and decision_id (shared across all tasks in the crew run). Ghost SDK fires asynchronously — no blocking of the crew pipeline. The decision_id UUID generated at crew entry links all task records, enabling full pipeline reconstruction by querying by decision_id.

Flows @listen Decorators as Compliance Capture Points

CrewAI Flows use @start and @listen decorators to define state machine pipelines. Each @listen method is a natural compliance capture point: the flow is between states, you have the complete current state, and the decision that caused the transition. Ghost SDK captures at each @listen method with the current state as context and the state transition as the action. The Flows pattern is especially useful for multi-stage decisions (e.g., coverage analysis → adjudication → payment approval) where each stage requires a separate compliance record with the same decision_id.

step_callback for Tool-Use Capture in Hierarchical Crews

CrewAI's hierarchical process uses a manager agent to delegate to worker agents. The step_callback parameter on the Crew fires after every agent action step — including tool calls, which are the most consequential actions in most crews. In the step_callback, check agent_action.tool to filter for substantive tool calls (excluding delegation steps) and capture with Ghost SDK. This pattern captures decisions at the tool-use level rather than the task level — more granular but also higher volume. Use step_callback for crews where tool calls have direct real-world effects (database writes, API calls, notifications).

Framework Compliance Requirements for CrewAI

EU AI Act Article 12: task callback records must include complete task input as context, agent role in metadata, task output as action, and subject_id — linked by decision_id for full pipeline reconstruction. HIPAA §164.312(b): subject_id must use internal patient identifier (not raw PHI in the record), context field should capture data references rather than raw PHI, retain records for 6 years, encrypt in transit and at rest. SOC 2 CC7.2: establish decision_type distribution baselines at deployment; alert when task completion rates or output semantic similarity deviate beyond threshold. GDPR Article 22: per-subject records retrievable by subject_id for data subject access requests; crew task structure provides the logical explanation of decision reasoning.