Weekly customer interview digest in Slack from call recordings

Build a weekly customer-feedback digest from raw interview and user-call recordings that my team drops into a Google Drive folder.

Trigger: cron, every Monday at 9am America/New_York. Google Drive is not a poll provider, so cron plus a filtered List Files call is the right pattern here, not a poll trigger.

Step 1: Use the google-drive List Files operation to find every audio file added to a configured Drive folder ID in the last 7 days. Use a Drive query like `'<folderId>' in parents and mimeType contains 'audio/' and createdTime > '<sevenDaysAgoISO>' and trashed = false`. Page through results until all matching files are collected. The folder ID should be a configurable input.

Step 2: For each matching file, call google-drive Download File Content to fetch the raw audio bytes.

Step 3: For each recording, push it through AssemblyAI. Call Upload Audio File to stream the bytes to AssemblyAI and get an upload URL. Then call Submit Transcript with that upload URL and these options enabled: speaker_labels: true, sentiment_analysis: true, entity_detection: true. Then call Get Transcript and poll until status is `completed`. If the polled status is `error`, log it and skip that file rather than failing the whole run.

Step 4: Once all transcripts are in hand, the agent should: (a) cluster the conversations into 3 to 6 recurring themes (for example 'onboarding friction', 'billing confusion', 'feature request: SSO') with punchy, specific theme names; (b) for each theme pick the single sharpest verbatim quote, attribute it with the AssemblyAI speaker label, and count how many distinct interviews touched that theme; (c) call out one or two notable outliers, meaning surprising or strong-signal moments worth flagging even if they did not cluster into a theme.

Step 5: Post the digest as a single message to a configured Slack channel (default #product-feedback) using the slack Send a Message operation. Format it as: a one-line intro with the date range and the number of interviews processed, one bullet per theme with the bolded theme name, the interview count in parentheses, and the verbatim quote on the line underneath, and finally a short 'Outliers' section at the bottom. Use Slack mrkdwn formatting (`*bold*`, not `**bold**`).

If no audio files were found in the last 7 days, post a short 'no new interviews this week' note to the same channel instead of skipping silently, so the team always knows the workflow ran.

This is an agent workflow (not code) because clustering, quote selection, theme naming, and outlier identification are open-ended judgement calls. The agent should reason over the full set of transcripts rather than following a rigid script.

Additional information

What does this prompt do?

Picks up every interview and user call recording your team dropped into a Google Drive folder over the last seven days.
Transcribes each conversation with speaker labels, so the digest can quote the customer and not the interviewer.
Clusters everything into three to six recurring themes like onboarding friction, billing confusion, or feature requests, with the sharpest verbatim quote under each.
Posts a single, scannable digest to your product feedback Slack channel before your Monday standup, plus a short callout of one or two notable outliers.

What do I need to use this?

A Google Drive folder where your team drops customer interview and user call recordings.
A Google account with read access to that folder.
An AssemblyAI account (used to transcribe the recordings).
A Slack workspace and the channel you want the weekly digest posted in.

How can I customize it?

Change when the digest runs (daily, weekly, biweekly) and the time zone it lands in.
Point it at a different Drive folder, or have it watch multiple folders for different research tracks.
Tweak how many themes you want surfaced, and the Slack channel or DM it posts to.
Tag specific teammates automatically when certain themes (like churn risk or pricing) show up.

Frequently asked questions

What kinds of recordings does this work with?

Any standard audio file dropped into the watched Google Drive folder, including mp3, wav, m4a, and similar formats. The workflow looks at audio files added in the last seven days.

Can I feed it Zoom, Gong, or Granola recordings?

Yes, as long as the audio files end up in the Google Drive folder. Most teams already auto-export their call recordings to Drive, so this hooks into that existing pipeline.

What if no new recordings were added that week?

The workflow posts a short 'no new interviews this week' note instead of skipping. That way you always know it ran, and a quiet week is itself a signal.

Will it figure out which speaker is the customer?

Each recording is transcribed with speaker labels, and the agent uses the conversation context to tell the interviewer apart from the customer when it picks quotes.

How long does each Monday run take?

Most teams see five to fifteen minutes per run, depending on how many recordings dropped that week. It runs on a schedule, so you just see the digest land in Slack.

Can I share the digest with a wider audience?

Yes. You can change the destination to a broader channel like #all-product or #leadership, or have it cross-post to multiple channels.