APPS:
Justin Nakano @ Zapier
Consolidate data from multiple sources into a daily Slack update that highlights growth across large accounts.
This visibility into upmarket customer growth helps the Revenue Operations team understand marketing campaign effectiveness, optimize sales routing, and anticipate renewal cycles.
How it works
This workflow uses Looker to retrieve key data from the warehouse through SQL queries or prebuilt Looks. It then uses AI to align relevant account-specific metrics and deliver the information in a streamlined daily Slack message.
Retrieve key data from the warehouse using SQL queries or prebuilt Looks via the Looker Zap.
Highlight trending metrics based on the retrieved data.
Use AI to align and contextualize account-specific metrics.
Automatically deliver the consolidated information in a daily Slack message.
AI and code steps
Code step: Extract column names and filter rows based on Account ID.
The Code step:
Extracts column names and their values from
inputData.Splits each column's values by comma and stores them in rows.
Extracts filter values from the input data.
Filters rows based on matching Account IDs.
Flattens the filtered rows into a single array that starts with the column names.
Outputs the combined array for the AI prompt.
AI prompt for Slack message: Use the combined account data to populate a consistent Slack message for every Account ID in the dataset. Format currency values as dollar amounts and include ARR, plan type, CSM ownership, task usage, and active users.
Impact
✔ Executive visibility: Execs can easily follow along with team progress.
⏱️ Time saved: Saves hours per week creating reports for cross-functional teams.
Related Workflows
