This playbook was originally published on G2 AI blueprints.
What problem does this solve?
Support hears every complaint first, but those insights reach product, ops and marketing late or not at all. Monthly tag reports lag and only count categories, CX leads don't have time to read hundreds of transcripts, and new issues get noticed only once the volume hurts. Product and merchandising decisions get made without the customer's own words in the room.
How does it work?
- Connect Claude to Yuma through the Yuma MCP, and connect Slack so Claude can post the report.
- Load the weekly voice-of-customer prompts into a Claude project so the same instructions run every week.
- Run the weekly scan: the last 7 days of tickets against a 4-week baseline. Ask for the top themes, the fastest-rising themes and any brand-new ones, each with a count, ticket IDs and a customer quote.
- Map every theme to an owner: product for defects and sizing, ops for shipping and missing items, marketing for promo confusion, CX for policy gaps.
- Audit before you send. Open two or three ticket IDs per flagged theme and drop anything that doesn't hold up.
- Post the digest to a shared Slack channel: three things to act on with owners, three to watch, and what customers praised.
- When a theme looks like a real problem, switch to a root-cause investigation for that one issue and pull the affected orders from Shopify.
- Schedule the scan to run every week. During peak season, run it daily over the last 24 hours.
- Close the loop. When a theme turns out to be a policy gap, update the Handbook so the agent answers it correctly next time.
What's the biggest win?
Support becomes the company's fastest customer research channel. Product, ops and marketing get a short weekly read of what customers are saying, in their own words and with evidence attached, instead of a lagging tag report. Emerging issues get flagged in the week they start rather than the month after, and praise reaches the teams who earned it.
What's required to run this?
Compare every week against a rolling 4-week baseline so seasonal volume doesn't trigger false alarms. Give Claude last week's digest as context and keep theme names stable, so trends stay comparable week to week. Ask for ticket IDs on every theme and spot-check them before posting. Keep the Slack post short and put the full theme list in a thread. Include what customers praised, since that keeps teams outside support reading the channel. Try it on your own tickets with a 30-day free Yuma trial.
What are the constraints?
Coverage is limited to conversations that flow through Yuma. Themes are AI-generated groupings that can merge or split differently between runs, so a human review stays in the loop. Stores with low ticket volume may not have enough data for weekly trends and should run it every two weeks or monthly. Posting to Slack requires Slack connected to Claude. The digest surfaces signals, not root causes; confirming a cause still needs a dedicated investigation.
The prompts for this playbook
Use these with Claude connected to Yuma through the Yuma MCP, and Slack if you want Claude to post the digest. Replace everything in [brackets]. Save them in a Claude project so they run the same way every week.
Prompt 1: weekly scan
Search every support ticket in Yuma from the last 7 days. Compare with the 4 weeks before that as a baseline.
Return:
1. The top 10 themes by volume, with ticket count and change versus the weekly baseline average.
2. The 3 fastest-rising themes (largest percentage increase with at least [10] tickets).
3. Any brand-new theme that didn't appear in the baseline at all.
For every theme give: a short stable name, ticket count, change versus baseline, the products or SKUs it clusters around if any, 2 ticket IDs and one short customer quote.
Here is last week's digest for context. Reuse the same theme names where the theme is the same: [paste last week's digest, or "none" for the first run].
Prompt 2: assign owners
For each theme from Prompt 1, assign one owner team:
- Product: defects, quality, sizing, missing features
- Ops and fulfillment: shipping delays, missing or wrong items, damage
- Marketing: promo or discount confusion, misleading product pages
- CX: policy gaps, unclear return or warranty rules
- [Add or rename teams to match your company]
Say in one line why each theme belongs to that team.
Prompt 3: write the Slack digest
Write the weekly voice-of-customer digest for [#channel-name]. Keep it under 250 words:
- One-line headline: the single most important thing this week
- Act on: 3 themes that need action, each with owner, count, change and one quote
- Watch: 3 themes that are rising but not urgent yet
- Praise: what customers loved this week, with one quote
- Link to the full theme list in a thread reply
Use plain language, no jargon. Do not post until I approve the draft.
Prompt 4: deep dive on a flagged theme
Take the theme [theme name] from this week's scan. List every matching ticket with ticket ID, date, order number and SKU if present, and a one-line quote. Flag uncertain matches. Group by SKU, order date, fulfillment location and carrier, and tell me whether this looks like a single root cause worth escalating.
Prompt 5: peak-season mode
Run Prompt 1 for the last 24 hours instead of 7 days, and compare with the same weekday last week. Flag any theme that has more than doubled. Keep the digest to 5 lines.
Rules to keep
- Spot-check ticket IDs for every theme you flag before the digest goes out.
- Keep theme names stable so week-over-week trends stay comparable.
- The digest surfaces signals. Confirm root causes with a proper investigation before acting.
