Skip to main content
A chat is a conversation against a knowledge base. When you send a message, AutoSage doesn’t answer from thin air — it can search your documents, query connected databases and chart the results, use connected apps and tools, and cite supporting sources. Streaming responses can show live progress before delivering the final answer. The same chat engine powers both dashboard conversations and agent runs, so what you learn here applies everywhere in AutoSage.

​
What a chat can do

Search your documents

Finds the most relevant passages in the knowledge base and cites them in the answer.

Query connected data

Runs read queries against connected databases and can chart the results inline.

Use tools and apps

Calls connected apps, custom tools, and other agents to go beyond the documents.

Cite its sources

Shows where each part of the answer came from, so you can verify it.

​
How a chat is organized

Every chat belongs to a tenant and a knowledge base, and each one carries a privacy level that controls who can see it.
1

Tenant

The resource owner the chat runs under — its credits and quotas apply to the conversation.
2

Knowledge base

The content the chat is grounded in: documents, database connections, prompts, and tools.
3

Privacy level

Private, Organization, or Public — determines who can view the conversation. See Sharing a chat.
Because a chat is scoped to one knowledge base and tenant, its answers only ever draw on that knowledge base’s content. This keeps every conversation grounded in exactly the material you intend.

​
How a question gets answered

1

Understand the message

AutoSage reads your question along with the recent conversation so far.
2

Gather grounded context

It searches your documents, and when helpful runs data queries, uses tools, or recalls durable memory.
3

Compose the answer

The model writes a grounded response. Streaming shows live progress and delivers citations and final content as they become available.

​
Choosing how deeply to answer

Each message can be answered in one of two modes — a fast single-pass Quick mode or a thorough multi-step Deep mode. Pick the right one per message to balance speed and depth.

Compare the modes

See when to use Quick versus Deep answering.

​
Next steps

Quick vs Deep modes

Choose the right answering mode for each message.

Streaming responses

See how live responses arrive and what to expect.

Sharing a chat

Share a read-only transcript with your org or the world.

Long conversations

How AutoSage keeps lengthy chats fast and coherent.