Skip to Content
Docs are being rebuilt — start at Introduction → How it works.
AgentsAgent overviewWhat an agent is

What an agent is

An agent is a named AI employee configured for a job. It combines identity, instructions, model settings, knowledge, skills, capabilities, channels, and triggers into one reusable assistant.

Main parts

PartPurpose
ProfileName, description, avatar, welcome message, and system instructions.
AI modelProvider, model, and tuning parameters that control response behavior.
Response settingsTone and output format, including structured output when needed.
CapabilitiesHigh-level permissions such as file access, code execution, workflow management, or API access.
SkillsReusable playbooks or procedures the agent can load for specific work.
KnowledgeKnowledge bases the agent can read from or write to.
InterfacesCustom forms or UI surfaces that collect structured input before chat.
Integrations and triggersExternal systems and events that start or support agent work.
Channels and web embedPlaces users can reach the agent outside the builder.

How agents differ from normal chat

Normal chat is flexible. An agent is repeatable. Use an agent when the same role, rules, tools, and knowledge should apply every time.