Learn from conversations
 

Learning from conversations lets coaching users teach Spotter directly during a conversation. When a coaching user defines something or corrects an incorrect answer, that context is saved as a rule in memory, and applies to future questions on the same data model.

Enable learning from conversations

Learning from conversations is off by default and is enabled by the same Early Access option as Learn from a Liveboard.

To enable:

  1. Navigate to the Admin tab and select All Orgs.

  2. Select ThoughtSpot AI under Application settings.

  3. Click Edit for the Other AI features section and set Memory from Liveboards and conversations to Enabled.

  4. Click Save.

When this feature is not enabled:

  • No new memory can be written from conversation.

  • Spotter stops fetching and applying any previously generated memory.

  • Existing memory is not deleted; if the feature is re-enabled, all previously written memory becomes active again immediately.

  • Reference questions, business terms, and instructions are not affected.

Who can teach Spotter from conversation

Only users with coaching access can teach Spotter from conversations-- this includes users with data model coaching permissions, data model edit access, or admin access.

End users without coaching permissions cannot write data model memory in this release.

What triggers learning

Spotter does not learn from every message. Learning is triggered by explicit user intent.

For example:

  • "Remember this: [definition]"

  • "Always [do X]" / "Never [do Y]"

  • Corrective statements after an incorrect answer — for example, "No, vegetables are labeled as Produce."

  • "Correct. Save this."

Vague dissatisfaction (for example, "this looks off") does not trigger learning.

What is stored as memory

Conversation learning writes only rules: business definitions, constraints, and conventions scoped to the data model being queried. Rules are stored at the data model level and apply to all users querying that Model.

What conversation learning does not write:

Scope and limitations

  • Data model layer only — memory is scoped to the data model being queried in the current conversation.

  • Single data model per session — if a conversation spans multiple data models, memory is not written across them.

  • No auto-mode — memory writing from conversation is not supported in auto-mode.

  • Rules only — Recipes cannot currently be generated from conversation. You should test the question again after telling Spotter to remember a correction.

Permissions

Action Who can do it

Enable/ disable memory

Admins only

Write data model memory from conversation

Users with coaching permission, data model edit access, or admin access

View memory written from conversation

Any user with access to that data model
Was this page helpful?
×