What is the definition of Property "Updated at"

Hi Yanisa S., Please stand by as I search the Mixpanel knowledge base for an AI-powered answer. I normally take about 15 seconds or so. In case AI cannot answer your question, feel free to reach out to Mixpanel support at mixpanel.com/get-support. If you have follow-up questions for this thread, please tag me again with your question: @kapa.ai <follow-up question> 👋

“Updated at” is the user profile property $last_seen. It is automatically maintained by Mixpanel and stores the timestamp of the last time a user profile property was set or updated (via $set, $set_once, etc.). It: - Does not change when the user performs new events (only when the profile itself is updated). - Does not change for profile updates made via the UI. - Does not change if the update call includes $ignore_time: true. [User properties; Updated at meaning]

ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.

Let me check the knowledge base for you again. One moment! 📚

You can do this in a few different ways depending on where you’re querying from.

If your Mixpanel data is in Snowflake / BigQuery via Data Pipelines, you can write SQL that: - Buckets events by day (in your project timezone) - Counts events per user per daySnowflake example (single events table): [Snowflake queries]LBKSSELECT TO_DATE(CONVERT_TIMEZONE('UTC','<PROJECT_TIMEZONE> ', time)) AS event_date, distinct_id, COUNT(**) AS event_count FROM <DB_NAME> .<SCHEMA_NAME> .MP_MASTER_EVENT WHERE event_name = 'your event name' GROUP BY event_date, distinct_id ORDER BY event_date, distinct_id;LBKSBigQuery example (single events table): [BigQuery queries]LBKSSELECT DATE(time, '<PROJECT_TIMEZONE> ') AS event_date, distinct_id, COUNT(**) AS event_count FROM `<PROJECT_DATASET> .mp_master_event` WHERE event_name = 'your event name' GROUP BY event_date, distinct_id ORDER BY event_date, distinct_id;LBKSThis gives you: one row per user per day with the number of times they did the event on that day.

You can also do this with JQL by: - Fetching events with Events({ from_date, to_date }) - Grouping by user and by day using groupByUser with an additional key (day) [groupByUser].Example pattern (simplified): js function main() { return Events({ from_date: "2025-01-01", to_date: "2025-01-07", event_selectors: [{ event: "your event name" }] }) .groupByUser([getDay], function(count, events) { count = count || 0; return count + events.length; // number of events for that user on that day }); }LBKSfunction getDay(event) { return (new Date(event.time)).toISOString().split('T')[0]; // YYYY-MM-DD }LBKSEach result row’s key will be [distinct_id, "YYYY-MM-DD"] and value will be the count for that user on that day. [groupByUser]---If you tell me whether you’re using Data Pipelines (and which warehouse) or JQL, I can adapt the exact query for you.

ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.