Promote Products: Claude + Make

What this does: every new product gets social posts written by Claude and queued in Buffer, so each launch promotes itself for your approval.

Time to set up: about 20 minutes once. After that adding a product also drafts its announcement.

What you need: a Make account (free tier is fine), a Claude API key, a Shopify store, and a Buffer account.

Skip if: you launch products rarely, or you plan every social post by hand.

Want a working AI workflow in your inbox each morning? Join the free daily Beginners in AI newsletter.

A streetwear label lives on drops, and every release is supposed to hit Instagram and X the moment it goes up. In practice the product gets added to Shopify at midnight and the social posts get written, maybe, two days later when the hype has cooled. The launch and the announcement keep missing each other.

This build syncs them. The moment a new product is added, Claude writes a launch post for each platform, and Make queues them in Buffer for a quick approval. The drop and its announcement go out together, while you stay the one who hits post.

We wire it in Make, the last build in our e-commerce set, and a cousin of our blog-to-social guide pointed at products. Buffer holds the posts for your approval, so nothing goes live unread.

What does this workflow actually do?

In one line: a new product becomes queued social posts. Make watches Shopify for new products. When one appears, Claude writes a post for each platform, and Make queues them in Buffer. You review the queue and approve; nothing posts on its own.

A few real cases, none of them the usual ones:

  • The streetwear label above, every drop announced the moment it lands.
  • An indie bookstore promoting new arrivals without a daily social chore.
  • A coffee roaster announcing each new single-origin to followers.
  • A maker of limited runs announcing every small batch before it sells out.

Adding the product is the work you do anyway. Writing and scheduling the launch posts is the step that lags behind the drop. That writing is exactly what Claude does instantly.

Why use Make if Claude can already read and write?

Fair question. Claude is good at writing a punchy launch post tuned to each platform. It is not built to watch Shopify and queue posts in Buffer. That is plumbing, and Make does plumbing.

Make handles the no-judgment steps: catching the new product, queuing each post, running on its own. Claude handles the one step that needs words, the announcement. Make is the scheduler; Claude is the copywriter. Buffer’s queue keeps a human approving, so a launch post never goes out with the wrong price or a typo in the drop name.

What do you need before you start?

  • A Make account. The free 1,000 operations a month covers regular launches.
  • A Claude API key from the console, not the chat app. See how to use Claude.
  • A Shopify store connected to Make.
  • A Buffer account with your social channels connected.

Two Make words. A scenario is the whole product-to-social automation. A module is one box. Three boxes, one scenario.

How does the workflow work, step by step?

Three modules, left to right:

ModuleAppWhat it does
1. TriggerShopifyFires when a new product is created
2. BrainClaudeWrites a launch post for each platform
3. OutputBufferQueues the posts for your approval
Make scenario: Shopify to Claude to Buffer, three connected modules
The finished scenario in Make: a Shopify product trigger, a Claude step, and a Buffer action, wired left to right.

Step 1: Watch Shopify for new products

Create a scenario and add Shopify, Watch products, connect your store, and watch for new products. This trigger hands the next step the product’s name, description, and link.

Step 2: Let Claude write the posts

Add a Claude module, Create a Prompt, paste your key, pick Sonnet:

Write launch social posts for this new product.
Name: {{title from Step 1}}
Details: {{description from Step 1}}
Link: {{product URL from Step 1}}

An Instagram caption (punchy, 1-2 lines, a few tags) and an X post
(under 280 chars, one link). Label them IG: and X:. No fake scarcity.

The labels let Make split the two posts, and banning fake scarcity keeps the launch trustworthy.

Step 3: Queue them in Buffer

Add Buffer, Create a status update, connect Buffer, pick your channels, and map each labeled post. Set Buffer to add to queue, not post immediately, so you approve each launch before it goes out.

How do you run it and check the result?

Click Run once on a test product. When I tested this, the IG and X posts came out usable, with the X one needing a tighter first line, a ten-second fix in the Buffer queue. Tune the Step 2 voice, keep Buffer on add-to-queue, then turn the scenario on so every product drafts its own launch.

After that, the drop and the announcement stop missing each other. You add a product, glance at the queued posts, approve, and the launch goes out on time instead of two days late.

What does this cost to run?

PieceFree tierIf you outgrow it
Make1,000 operations/month freeCore plan from about $9/month
Claude APIPay per useTwo launch posts on Sonnet cost a fraction of a cent
ShopifyYour existing planNo extra cost
BufferFree plan covers a few channelsPaid from about $6/channel/month

Each product is three Make operations and a sliver of Claude. The build sits inside the free plans. More on tiers in our Make guide.

What can go wrong, and how do you avoid it?

  • Posts go out unreviewed. Set Buffer to add-to-queue, not post immediately, so you approve first.
  • The price or name is wrong. Review the queue; a launch post with a wrong price is worse than a late one.
  • It uses fake scarcity. Ban it in the prompt; “only 3 left” that is not true erodes trust.
  • It fires on old products on first run. Normal; clear the test posts from Buffer.

The same product-to-social pattern runs many jobs. See Make AI scenarios.

How do you build this in Zapier or n8n instead?

The three jobs do not change, only the names do.

JobMakeZapiern8n
Catch a productWatch productsNew Product triggerShopify Trigger node
Write the postsClaude moduleClaude (Anthropic) actionAnthropic node
Queue to socialCreate a status updateBuffer actionBuffer node

Make and Zapier are easiest to start. Zapier vs Make vs n8n compares all three.

Want the ready-made template?

The steps above build it from scratch. If you would rather skip the setup, the importable Make blueprint is yours free: subscribe to the daily newsletter and the download is waiting on the thank-you page, next to our Special Reports. Import it, connect your own accounts, and you are running in minutes.

Subscribe free and grab the template →

Want it set up with you, live?

Book a 1-on-1 Live Claude AI Crash Course and we build your first automation together, screen to screen.

Book the 1-on-1 ($75) →

Want better prompts for it?

The AI Prompt Library includes launch-post and product-promo prompts you can paste into Step 2.

Get the Prompt Library ($39) →

Launch the drop and the post together

Free daily newsletter. Built for people who want to use AI well, not chase every model.

Free forever. Unsubscribe anytime.

Common questions

Does it post to social automatically?

No. Buffer holds the posts in a queue for your approval, so you catch a wrong price or name before a launch goes out.

Can it post to more than two platforms?

Yes. Buffer supports more channels; add them in the Buffer step and ask Claude for a post per platform.

Does it include the product image?

You add images in Buffer, or extend the flow to pull the product photo. Start with text and the link.

Will it work with WooCommerce?

Yes. Swap the Shopify trigger for WooCommerce; the Claude and Buffer steps are the same.

Is the chat app the same as the API?

Same models, different door. Make needs an API key from the console, not the chat login.

Primary sources

Last reviewed: May 2026. Make, Claude, Shopify, and Buffer update their interfaces; check the official pages for exact button names.

You may also like

Two ways to go further

The AI Prompt Library

1,000+ ready-to-use prompts for Claude, ChatGPT, and Gemini. Stop staring at a blank box.

Get it for $39 →

2-Hour Live AI Crash Course

A private, beginner-friendly session across Claude, ChatGPT, Gemini, and the wider landscape.

Book for $125 →

Discover more from Beginners in AI

Subscribe now to keep reading and get access to the full archive.

Continue reading