Goal-driven AI Agents that operate as first-class platform entities across Torq. They are not limited to workflows. AI Agents power Socrates conversations, enrich and reason over cases in Case Management, contribute to Auto Triage decisions, and can be invoked as tools inside other agents, creating composable multi-agent systems. Fully customizable and adaptable, they can be tailored to support a wide range of use cases across security, IT, and more.

Traditional deterministic workflows require defining every condition and edge case, a rigid, time-consuming process. AI Agents bring adaptive intelligence that responds to change while maintaining boundaries and adhering to the rules you define.

Yes. Guardrails are explicit instructions you add to an Agent’s configuration to guide its behavior. They help prevent hallucinations, cut down on unnecessary verbosity, and keep outputs consistent and dependable for downstream automation. Agents always operate within defined boundaries: their assigned mission instructions and the toolbox of steps or workflows they are allowed to use. While they act autonomously, every action is logged in the Action Flow for full visibility and auditability. Guardrails are further reinforced by access policies and, when required, approval layers built into the tools the Agent can call.

AI Agents are fully configurable building blocks across the Torq platform. They use AI models to take on a defined role, follow instructions, and call tools dynamically. They are customizable and domain-specific: tailor them to your exact SOC, IT, or operations use case, then publish them for use across Auto Triage, Case Management, security automations, and Socrates.
Socrates is Torq's conversational AI interface, powered by AI Agents. When starting or switching a conversation, you select which agent governs it: the built-in Investigator and Builder system agents, or any custom agents your team has published. This means every published agent is immediately available for real-time, conversational interaction inside Socrates.

Once published, an AI Agent is available across the entire Torq platform without additional setup: Auto Triage enrichment, Case Management, Socrates conversations, and security automation workflows. Agents can also be invoked as tools inside other agents, enabling multi-agent collaboration within a single workspace.

Yes. Published AI Agents can be used as tools inside other agents or Socrates conversations, enabling composable multi-agent systems natively within Torq. This allows you to build specialized agents and chain them together for more complex tasks.

Yes. Agents built inside workflows are moving to the AI Agent hub, where they live in one shared place and can be reused across the workspace. To keep workflows running, migrate each flagged agent to the hub and replace the legacy step on the canvas. For details, see AI Agents: Migrate Workflow Agents to the AI Agent Hub.

Yes. AI Agents are available across all tiers through a credit-based pricing model. This model combines tier-based entitlements with flexible add-on options, allowing teams to scale usage based on their needs. Whether you're just getting started or running large-scale workflows, you can tailor your AI Agent usage without moving to a different plan.

Rate limits depend on the model type you're using:

While there's no limit to the number of tools you can assign to an AI Agent’s toolbox, each execution is limited to a maximum of 25 tool calls.

AI Agents are designed for adaptive, context-aware behavior, so their operation and outcomes may vary between workflow runs. If your use case demands identical results every time, consider using a more deterministic workflow design instead.