Skip to main content
Version: 1.0.0-beta

Agentic AI

AIIA's Agentic AI enables autonomous audit assistants that can perform multi-step tasks under human supervision. Unlike simple one-shot suggestions, agentic AI can plan, execute, and iterate on complex audit activities.

What Are AI Agents?​

AI agents in AIIA are specialized assistants that can:

  • Break complex tasks into steps
  • Execute multiple actions in sequence
  • Use tools (search, analyze, calculate)
  • Produce structured outputs
  • Request human approval at decision points

Available Agents​

AgentPurposeKey Capabilities
Audit CompanionGeneral-purpose audit assistantAnswer questions, search history, explain standards
Data AgentData analysis and queryingNatural language queries, visualization, trend detection
Scoping AgentEngagement scoping assistanceRisk assessment, scope recommendations, methodology suggestions
Review AgentWorkpaper review helperQuality checks, completeness verification, consistency review

AI Governance for Agents​

Agentic AI follows strict governance rules:

  1. Suggestion-only outputs — agents never modify data directly
  2. Human-in-the-loop — approval required at each action step
  3. Full audit trail — every agent action is logged
  4. RBAC enforcement — agents can only access data the user can access
  5. Bounded execution — agents have defined scope limits

Using the Audit Companion​

The Audit Companion is available as a sidebar chat:

  1. Click the AI Companion icon (🤖) in the sidebar
  2. Ask questions in natural language
  3. The companion can search your audit data, reference standards, and suggest actions
  4. All conversations are logged

Permissions​

RoleCan Use Agents
Auditor✅
Manager✅
CAE✅
QA✅ Read-only queries
Client❌