Spotter memory
Memory is the new context that Spotter 3 uses when answering questions. Memory can be generated from Liveboards you specify, and from corrections you make in conversations.
The key difference from existing coaching is that memory is generated by the AI from the sources listed above-- you do not author it manually. When conflicts arise between memory entries, they are resolved automatically.
| In the future, all coaching workflows will move to the memory format. For now, memory is additive; your existing reference questions, business terms, and instructions are not affected and continue to work exactly as before. |
Types of memory
Learnings are stored as memory in two formats:
- Rules
-
Business definitions, constraints, and conventions that should apply consistently. Similar to instructions.
- Example
-
"Revenue always excludes returns." Rules are generated from both Liveboard learning and conversation learning.
- Recipes
-
Proven query patterns capturing the exact columns, filters, and computation steps behind a trusted answer. Similar to reference questions.
- Example
-
"MTTR by priority — use cohort-based events filtered to last month." Recipes are generated from Liveboards only.
How memory is built
- Learning from Liveboards
-
Spotter analyzes a trusted Liveboard and generates memory from the charts and their underlying queries.
- Learning from conversation
-
When a user with coaching privileges defines or corrects something during a conversation, that context is saved as memory and applies to future questions on the same data model.
Key capabilities
- Column-level security
-
Like instructions, memory context participates in Spotter’s reasoning and may reference column names. Column-level access controls are enforced at query execution — column values from restricted columns are never returned in results.
- Multilingual
-
Memory works across languages. A memory entry written in one language applies when questions are asked in another.
Limitations
- Spotter 3
-
Memory is only generated and applied when Spotter 3 is enabled for your Org.
- Migration
-
Memory cannot be migrated between Orgs and instances.
- Syncing
-
Memory does not automatically sync with data model changes.
