Compare Agentic Assistant with Cortex Assistant - Feature comparison between Cortex Agentic Assistant and Cortex Assistant. - Administrator Guide - Cortex XSIAM - Cortex - Security Operations

Cortex XSIAM 3.x Documentation

Product
Cortex XSIAM
Creation date
2025-07-15
Last date published
2026-06-04
Category
Administrator Guide
Abstract

Feature comparison between Cortex Agentic Assistant and Cortex Assistant.

Cortex XSIAM offers two distinct forms of AI-driven assistance. Agentic Assistant is an advanced, optional capability that utilizes generative AI to autonomously plan and execute complex workflows. Cortex Assistant is a basic interface for streamlined navigation and entity investigation using natural language.

The following details the differences between Agentic Assistant and Cortex Assistant.

Features

Agentic Assistant

Cortex Assistant

How it operates

Uses a Large Language Model (LLM) to analyze intent and dynamically generate a plan, a unique sequence of actions executed step-by-step to resolve a specific request.

Uses natural language processing to convert user questions into XQL queries and suggest a list of static, predefined responses (for example, "Run Playbook," "Scan Host").

Scope of operation

Complex, ad-hoc scenarios. Agents function as virtual personas (for example, Threat Intel, IT) that can autonomously determine the necessary steps to achieve a broad objective.

Routine tasks such as single-entity investigations (host, hash, user) and navigation shortcuts.

Customization

Anyone with the relevant permissions can build custom agents with specific instructions, personas, and restricted sets of actions. Scripts and commands can be registered as new actions for agents to utilize.

Functionality is limited to out-of-the-box capabilities provided by the platform. You cannot modify Cortex Assistant's behavior.

Execution logic

Agents validate their own plans, clarify ambiguous prompts, and execute multiple steps in sequence or parallel based on the context of the investigation.

Relies on traditional rule-based automation. Actions are discrete and require manual selection from a recommended list.

Infrastructure

Leverages dedicated Google Cloud Platform (GCP) infrastructure for GenAI processing.

Processes queries within the standard tenant infrastructure.

Availability

Disabled by default. It requires enablement by an Administrator via SettingsConfigurationsGeneralServer SettingsAgentic Assistant and is currently restricted to tenants in specific regions. For more information, see Cortex Agentic Assistant.Cortex Agentic Assistant

Available by default to all tenants not using Cortex Agentic Assistant.

Access Control (RBAC)

Administrators use a dedicated CORTEX AGENTIC ASSISTANT permission category to configure specific permissions for:    

  • Interacting with agents using the chat interface.

  • Managing agents/actions: Viewing, creating, or editing custom agents and registering new actions in the Agents Hub.

Permissions are determined by standard Cortex XSIAM user roles (for example, View/Edit access to specific modules).

Auditing

All agent activities are logged in a specific dataset (agentix_agents_actions) queryable via XQL. You can also view the specific plan generated by the AI within the chat interface to understand the logic behind an answer.

Actions taken are logged as standard system activities.