LLMs.txt directory

Where to write context

Six places, one question each. Pick the surface whose question matches what you want Spotter to do.

The surfaces

Surface Where Answers the question Reaches the agent Example

Spotter instructions

Spotter settings, Org level

How should the agent behave, for everyone?

Always, in the system prompt

"End revenue answers with 'Figures unaudited'."

Analyst instructions

On a Spotter Analyst

How should this team’s analyst behave and what should it focus on?

Always, in place of the Org instructions, for conversations in that Analyst

"You are the EMEA renewals analyst. Lead with churn risk."

Column synonyms

Model column property

What else do people call this column?

During column matching

region: geo, territory

AI Context

Spotter optimization tab, 400 characters per column

What is this column and how are its values written?

During column selection; into the prompt only for selected columns

"Fiscal quarter label, e.g. Q2 FY26. Fiscal year starts February."

Data model memory

Memory sources, from Liveboards and conversations

What business logic applies to this Model, and how are recurring analyses built?

Retrieved by meaning, per question. A learned analysis is applied as-is on an exact match, else as a pattern

"Churn = churned ARR plus downgrades." "Quarterly churn: filter close_date to the quarter, group by month, sum arr_change."

Personal memory

Said in conversation, no editor

What should Spotter remember about me?

Profile always; preferences by relevance on that Model

"When I say my accounts, I mean EMEA enterprise."

Data model instructions, reference questions and business terms you wrote earlier stay in place and are fetched like memory. See Legacy memory sources and Data model instructions.

Same fact, different homes

What happens to one sentence depending on where it is written. ✅ marks the home to use.

Expectation Data model semantics Spotter instructions Memory

Revenue excludes internal test accounts

On the revenue column. Seen only if revenue is already picked. The filter lives on a different column (account type), so the agent has to connect them itself

A data fact, not behavior. It would apply to every Model in the Org.

✅ Data model memory. Retrieved whenever revenue is asked about, names both columns, applied as a filter.

Bookings use Close Date, not Created Date

"Prefer this over Created Date" on Close Date is a preference, not a description. It only helps once Close Date is a candidate

A data fact, not behavior

✅ Data model memory: "Bookings questions use Close Date." Plus AI Context on each column stating what it is: "Date the deal was signed" vs "Date the record was created."

End every answer with "Figures unaudited"

Not about a column. No home here

✅ Spotter instructions. Applied to every answer, never filtered out

Retrieved only when the question happens to match, so it fires sometimes.

Churn equals churned ARR plus downgrades

Could go on arr_change, but the definition spans change_type too, and it only matters when churn is asked

A definition, not behavior

✅ Data model memory. Everyone asking about churn on this Model gets the same definition.

Medicine names are stored as short forms, MP means Metoprolol

✅ AI Context on the medicine column. This is how the values are written, exactly what column selection needs

Too specific for behavior instructions

Would also work, but the fact is about one column’s values, so keep it with the column.

My team says "geo" for region

✅ Synonym on the region column. A name-to-column mapping, used directly in matching

Not behavior

Would also work, but a name for one column belongs on the column.

When I say "my accounts", I mean EMEA enterprise

Not about a column. True for one person only

It would apply to everyone in the Org

✅ Personal memory. Say it in conversation; it filters your answers and nobody else’s.

Next