Skip to main content
AutoSage keeps long conversations running smoothly. As a chat grows large, it automatically summarizes the older parts of the conversation while keeping recent messages verbatim. This process — called compaction — lets the assistant stay consistent and responsive without re-reading the entire history on every message.

​
What compaction preserves

Compaction is designed to hold onto the details that matter over a long conversation:

Preferences

How you like things done, carried forward as the chat grows.

Decisions

Choices you’ve made earlier in the conversation.

Constraints

Requirements and boundaries the assistant should keep respecting.

Open tasks

Work still in progress that the summary identifies as relevant.
Recent messages stay exactly as written, while older context is distilled into a summary. This provides best-effort continuity, but a summary can omit details; restate critical constraints when they matter.
Compaction happens automatically and transparently. There’s nothing to configure and nothing to turn on — long chats simply keep working.

​
Compaction vs. Memory

Compaction and Memory both help the assistant remember, but they work at different scopes:
CompactionMemory
ScopeA single long conversationAcross separate conversations
PurposeKeep one chat coherent as it growsCarry durable facts between chats
SetupAutomaticConfigured per tenant and knowledge base

Learn about Memory

How durable facts carry across different conversations.

​
Getting the best results

When you move on to a genuinely new topic, start a new chat rather than continuing a long, unrelated one. A fresh chat keeps answers focused on the task at hand — and costs less than carrying a long history that no longer applies.

​
Next steps

Chat overview

How grounded, cited answers come together.

Memory

Carry durable facts across separate conversations.

Quick vs Deep modes

Choose how deeply each message is answered.

Sharing a chat

Share a read-only transcript of a conversation.