Agent

Understand conversation-oriented models, knowledge, tools, memory, and the publish lifecycle

An Agent is an AI application for multi-turn conversations. It combines a chat model authorized to a team with system prompts, variables, Knowledge Bases, tools, memory, attachments, and media generation settings.

Orchestration and runtime

The Agent editor page consists of an orchestration form and a live preview. Prompts support {{variable_name}}; user variables support text, paragraphs, dropdown options, numbers, and checkboxes. The system variable {{query}} represents the current user input.

An Agent performs up to 1-200 tool iterations per turn, with a default of 5. When the limit is reached, the turn terminates with max_iterations_reached instead of calling tools indefinitely.

RAG modes

Mode	Behavior
`off`	No Knowledge Base retrieval
`auto` (Naive RAG)	Automatically retrieves linked Knowledge Bases before each model call
`agentic` (default)	The Agent decides when to retrieve Knowledge Bases

Each linked Knowledge Base can independently configure its retrieval method, Top K, and threshold. The retrieval method is vector, fulltext, or hybrid.

Conversations, branching, and compression

A conversation is implicitly created with the first message. Users can edit messages or regenerate replies; the system saves versions and maintains the active branch. Long conversations run a context budget check before model calls and can compress old reasoning, tool results, and historical turns while keeping recent raw turns.

Memory

With memory enabled, an Agent can retrieve user information across conversations. Each turn injects up to 10 memory entries by default, configurable from 1-50; automatic extraction is on by default, and the minimum importance defaults to medium. Memory differs from conversation context: conversation context belongs to a single conversation, while memory can be used across conversations.

Publishing and visibility

An Agent has only two states: Draft and Published. Visibility is Private or Team; legacy public values are normalized to team visibility for backward compatibility. After publishing, the public conversation page, embeddable page, and API are available; publish permission and edit permission are controlled separately.