Turn customer reviews into social, email and product page content

PromptCreate

Every Tuesday at 9am, turn my best new Yotpo reviews into marketing content my team can actually use. Run this on a cron schedule, weekly on Tuesday at 9am.

Start by pulling the past week's reviews from Yotpo with Retrieve All Reviews. The legacy Reviews API uses page plus count offset pagination, so keep requesting pages until you have covered the full week, then stop. Keep only the reviews rated 4 or 5 stars and discard the rest.

Use Yotpo Retrieve Products to pull the catalog and attach the correct product name to each remaining review, matching on the product identifier that comes back with the review. If a review cannot be matched to a product, say the product is unknown rather than guessing at it.

From that pool, pick the most vivid and specific quotes. Favour concrete detail, a reviewer describing exactly how they used the product or what changed for them, over generic praise like great product or love it. Aim for about 5 quotes per batch.

For each quote you pick, draft three things: a short social caption, a one line testimonial block for email, and a suggested product page pull quote. Keep the customer's own wording and trim only for length. Do not rewrite their voice, do not polish their grammar into marketing speak, and never invent a claim the reviewer did not make.

Attribute every quote using first names or initials only, never a full name. Skip any review that names a competitor, and skip any review containing personal details such as an email address, phone number, order number or street address. When in doubt, leave the review out.

Save the week's batch as a single Notion page in my content queue database using Create a Page. Give it a dated title, and under each quote include the product name, the star rating, the reviewer's first name or initials, the original quote, and the three drafts.

Then post a Slack message with Send a Message so marketing knows the queue is ready for review. Include how many quotes are in the batch and a link to the Notion page. This workflow stages content for human approval and does not publish anywhere.

What does this prompt do?

Collects the past week's customer reviews and keeps only the 4 and 5 star ones, with the right product name attached to each
Picks the most vivid, specific quotes and skips the generic 'great product' filler
Drafts three ready to use pieces per quote: a social caption, a one line email testimonial, and a product page pull quote
Saves the week's batch to your Notion content queue and tells the marketing team in Slack that it is ready to review

What do I need to use this?

A Yotpo account with reviews collected on your store
A Notion workspace with a content queue database where the weekly batch will be saved
A Slack workspace and the channel your marketing team watches

How can I customize it?

Change the star rating floor if you want to include 3 star reviews or keep it to 5 stars only
Move the run to a different day or time to match when your marketing team plans content
Adjust how many quotes land in each weekly batch, depending on how much your team can work through

FAQs

Does this post anything to social media automatically?

No. Everything is staged as drafts in your Notion content queue for a person to review, edit and approve. Nothing is published anywhere, which is the right call when you are using real customers' words.

Will it put customers' full names on our marketing?

No. Reviewers are credited with a first name or initials only. Any review that includes personal details like an email address, phone number or order number is skipped entirely.

Can it make claims our customers did not actually make?

It is instructed not to. The drafts keep the customer's own wording and are trimmed only for length, so the quotes stay accurate to what was written rather than being polished into marketing speak.

What happens in a week with very few good reviews?

You get a smaller batch. It only uses reviews that genuinely came in that week and meet your star rating floor, so the queue reflects real customer feedback rather than being padded out.

What if a review mentions a competitor?

It gets skipped. Reviews naming a competitor are left out of the batch so they never reach a draft caption or product page.

Related templates

Call overdue Xero customers with an AI collections agent

Every weekday at 10am, an AI voice agent phones your most overdue Xero accounts, logs what each customer promised, and reports back to finance in Slack.

+2

Agentic Task

Win back LiveChat visitors whose chats went unanswered

Every couple of hours we find the chats your team never answered, email those visitors a real reply, and hand the sensitive ones to a support lead.

Agentic Task

Chat quality review board for LiveChat support leads

Score last week's finished live chats against one rubric, let an AI grader draft the notes with quotes, and send coaching straight to the agent.

App

Win back no-show and cancelled appointments every morning

Every weekday morning, every appointment that fell through yesterday gets a personal text or email inviting them to rebook, plus a task for the right rep.

Agentic Task

Live Loop returns analytics with product-level drill-down

Pick any date range up to 120 days and see return volume, refund versus exchange mix, and the products behind every number, recalculated each time you open it.