Skip to main content
Each agent has an agent memory where the AI notes procedures and caveats learned from conversations with that agent. Manage it on the Memory tab of the agent detail page.
Personal memory, which stores your individual preferences, is managed separately. See Memory (personal settings).

​
How it works

  • During conversations with this agent, the AI writes down anything it judges worth remembering, as it happens
  • What it writes down is shared with everyone who uses this agent
  • It does not backfill from past logs. Learning starts with conversations after you turn it on

​
Turning learning on and off

Use the “Learn from conversations (shared with everyone)” switch on the Memory tab.
  • Turning it off stops new entries from being written (existing memories remain)

​
Viewing and managing memories

The Memory tab lists everything this agent has learned.
  • Members with edit permission can edit or delete each entry individually
  • View-only members (“Use only” permission) can read the entries but not change them
Agent memory works like a team-shared handover note. If the AI learns something incorrect, fix it by editing or deleting the entry.