Administration & observability · Reliability and controls
Which BI tools log what the AI assistant does?
8 of 15 tools do, according to their public docs, and 2 partly.
Yes: Databricks, Snowflake, Omni, Hex, Sigma, BigQuery, Looker, Metabase. Partly: Tableau, Power BI.
The question we asked: Are the built-in assistant’s actions logged with the user and the analytical objects affected?
Grading standard
The product records what the built-in assistant did, the prompt or query it ran and the objects it touched, attributable to the user who asked. A general product audit log that does not distinguish assistant activity is insufficient.
Databricks
Yes
Quoted from Databricks’s docsEach user sees only the data they are authorized to access, and each query is attributed to the end user in query history and the agent's monitoring page.
Source: docs.databricks.com/aws/en/genie-agents/concepts · checked Oct 26, 2026 · quoted by Claude
Snowflake
Yes
Quoted from Snowflake’s docsTogether, these columns help you reconstruct the causal chain that compliance teams often need: a user invoked an agent, specific queries followed, and specific objects were accessed.
Source: docs.snowflake.com/en/user-guide/agent-identity · checked Oct 26, 2026 · quoted by GPT
Omni
Yes
Quoted from Omni’s docsEach of these steps is logged individually in the tracking data, which is why a single user prompt can appear as several rows.
Source: docs.omni.co/ai/settings/usage · checked Oct 26, 2026 · quoted by Gemini
Hex
Yes
Quoted from Hex’s docsThis view lets you review individual turns in the conversation, inspect tool calls made by the agent, and see the primary data assets referenced at each stage.
Source: learn.hex.tech/docs/agent-management/observability · checked Oct 26, 2026 · quoted by Claude
Sigma
Yes
Quoted from Sigma’s docsFor example, for a Trace Name of database_execute_query, includes the SQL statement run for the tool call and the title shown to the user in the chat (if applicable) during the tool call.
Source: help.sigmacomputing.com/docs/ai-usage · checked Oct 26, 2026 · quoted by Claude
BigQuery
Yes
Quoted from BigQuery’s docs- Audit agent activity.
Source: docs.cloud.google.com/bigquery/docs/conversational-analytics · checked Oct 26, 2026 · quoted by Gemini
Looker
Yespreview
Quoted from Looker’s docsThe Responses & feedback tab reports information about Conversational Analytics user behavior for users who have consented to revealing their query data to their Looker admins.
Source: cloud.google.com/looker/docs/system-activity-dashboards · checked Oct 26, 2026 · quoted by Gemini
Tableau
Partly
Quoted from Tableau’s docsIt stores the prompt and response for every LLM API call along with other audit data for a maximum of 30 days in your Salesforce Data 360 instance.
Source: help.tableau.com/current/tableau/en-us/tableau_gai_usage.htm · checked Oct 26, 2026 · quoted by Gemini
Power BI
Partlypreview
Quoted from Power BI’s docsFrom here, you can select a semantic model and see what questions users have been asking.
Source: learn.microsoft.com/en-us/power-bi/natural-language/q-and-a-tooling-intro · checked Oct 26, 2026 · quoted by Claude
Metabase
Yes
Quoted from Metabase’s docsQueries generated: every SQL or query builder (MBQL) query Metabot wrote during the conversation, with the referenced tables listed underneath.
Source: www.metabase.com/docs/latest/ai/usage-auditing · checked Oct 26, 2026 · quoted by Claude
Alteryx
MotherDuck
Mode
No
Quoted from Mode’s docsBelow is a categorized list of events currently audited:
Source: mode.com/help/articles/audit-logs · checked Oct 26, 2026 · quoted by Claude
Redshift
Streamlit