Skip to Content
Agentic WorkspaceAI AgentOverview

AI Agent Overview

An AI Agent is an LLM-driven agent. Instead of a fixed graph, you give it an identity, a set of skills, tools, memory, and policies — and the LLM decides what to do at run time. It reasons about each request, picks the right tools, calls them, observes the results, and responds.

Use an AI Agent when the problem is open-ended — support assistants, research, question answering over your data, or any task where the exact steps aren’t known in advance. When you need a deterministic, auditable pipeline instead, build a Task Agent.

How an AI Agent differs from a Task Agent

AI AgentTask Agent
EngineLLM planning + tool callingVisual graph of nodes
BuilderForm-based editor with four tabsDrag-and-drop canvas
Control flowThe LLM decides the pathYou wire the path explicitly
Best forChat, assistants, open-ended tasksPredictable, step-by-step flows
ℹ️

A Task Agent can be attached to an AI Agent as a tool. This lets an AI Agent call a deterministic workflow when it needs one — see Attach tools.

What makes up an AI Agent

You configure an AI Agent across four tabs in the editor. Each maps to one part of the agent’s definition.

Identity

The agent’s name, an Administrative Summary (what it does), a Persona (personality, tone, and safety constraints), the Skills it can perform, and a Fallback message for requests it can’t handle. See Agent Identity.

Skills

A skill is a named capability — a description, matching tags, a system-prompt overlay, and a set of tools the agent may use for that skill. When a user message arrives, the agent matches it to the best skill and uses that skill’s tools and instructions. Skills are the richest part of an AI Agent. See Skills.

LLM Settings

Controls how the agent reasons: the reasoning mode, step and tool-call limits, extended thinking, and how much of its reasoning end users see. You can also pin a specific model and attach an LLM policy for guardrails. See LLM Settings.

Two reasoning modes are available:

ModeHow it works
ReActThe agent thinks and acts in interleaved steps — good for dynamic tasks.
Planner → ExecutorThe agent plans all steps first, then executes them — good for complex workflows.

Memory

Optional, opt-in memory across three tiers: Profile (user preferences), Episodic (past conversation summaries), and Semantic (a knowledge base plus self-learning). See Memory.

Modes

A mode is how the agent is used. You enable modes in the editor and at deployment time.

ModeDescriptionWhere it’s enabled
ConversationChat sessions with memory, via textEditor
Voice StarterReal-time voice using STT/TTS or a native realtime modelEditor
ScheduledCron-triggered autonomous runsOn a deployment
APIStateless REST endpoint for integrationsOn a deployment
ℹ️

Conversation and Voice are configured in the agent editor. Scheduled and API modes become available once the agent is deployed (added to a deployment, or deployed on its own). See Deploy.

The AI Agent lifecycle

  1. Create — Name the agent and pick its initial modes.
  2. Configure — Set identity, skills, LLM settings, memory, and modes.
  3. Test — Chat with the agent in the live preview; test governance with role impersonation.
  4. Version — Save your work as a draft version, and create new versions as you iterate.
  5. Publish — Promote a version to production.
  6. Deploy — Make it reachable at a URL, and enable Scheduled/API modes.

What’s next