Summarize daily Slack standups with OpenAI, Notion, and Google Sheets

Quick overview

This workflow runs every weekday, pulls standup messages from a Slack channel, uses OpenAI to generate a structured daily digest, saves the digest to a Notion database, posts a summary back to Slack, and appends an audit entry to Google Sheets.

How it works

1. Runs every weekday morning on a cron schedule.
2. Fetches the day’s recent messages from a specified Slack standup channel and filters out bot, subtype, and join/leave system messages.
3. Checks whether any standup messages remain and posts a Slack notice if none are found.
4. Formats the remaining Slack updates into a single structured prompt with date, team name, and message count.
5. Sends the formatted standup text to OpenAI (gpt-4.1-mini) to generate a JSON digest with summary, highlights, blockers, per-user updates, and mood.
6. Parses and enriches the AI output with metadata, creates a new page in a Notion database, posts the digest to a Slack summary channel, and appends a run record to a Google Sheets “Audit Log” sheet.

Setup

1. Add a Slack OAuth2 credential and set the standup channel ID (history source) and the summary channel ID (digest destination).
2. Add an OpenAI credential and confirm the model selection (gpt-4.1-mini) is available in your account.
3. Add a Notion credential, create/select a target database, and replace YOUR_NOTION_DATABASE_ID (and ensure the database has the referenced properties: Date, Team, Message Count, Mood).
4. Add a Google Sheets Service Account credential, share the target spreadsheet with the service account email, and replace YOUR_SHEET_ID and the sheet name (“Audit Log”) if different.
5. Adjust the schedule cron expression (0 9 * * 1-5) to match your team’s standup timing and timezone expectations.