Agent setup guide
Marketplace Price Watch
Every morning your price sheet and Shopify products are compared by SKU in code; any SKU with different prices is posted to Slack. It never changes a price.
What it does
Every morning your price sheet and Shopify products are compared by SKU in code; any SKU with different prices is posted to Slack. It never changes a price.
- Every morning, reads your price sheet (SKU | Product | Price) and your Shopify products.
- Groups every price by SKU in code, keeps the SKUs found in both and lists those whose prices differ, with each channel's price and the difference.
- AI adds a short note on what to check, without typing any prices.
- Posts the mismatches to your Slack channel; a day with none posts nothing.
What it needs
- A paid plan (agents run live on paid plans).
- An AI provider key (Settings → AI Providers).
- Google Sheets, Slack and Shopify, connected in Settings → Integrations.
- The same SKUs on your price sheet and in Shopify.
What it doesn't do
- It never changes a price.
- eBay and Amazon prices aren't read (our connections to them don't read listing prices).
- Products without a SKU aren't compared, and prices are compared as numbers (keep one currency).
- It reads up to 250 Shopify products per run.
Availability and plans
Available
Its workflow is built and tested, and every app it needs is live. You can get it and set it up now.
Included free on the Enterprise plan; on other paid plans it's a one-time purchase per workspace (the price is on the Agents page). The Agents page in the app always shows its current status.
Before you start
- A paid plan: agents run live, and the Free plan only runs Dry Runs.
- An AI provider key (OpenAI, Anthropic, Google and more) in Settings → AI Providers. AI usage is billed by your provider.
- These apps, connected in Settings → Integrations: Google Sheets, Shopify and Slack.
- Nothing to send: the agent runs on a schedule.
- About 15 minutes.
Set it up step by step
Get the agent first (buy it, or it's already yours when your plan includes it), then in Agents → My agents press “Set up this agent”. That creates the agent's workflow in your workspace (it counts towards your plan's workflow limit) and opens the canvas with a setup checklist above it. Each item links to the exact place to go and ticks itself off when it's done.
1. Connect your AI provider
The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.
2. Connect Google Sheets
Connect the Google account that can open your price sheet (Settings → Integrations → Google Sheets).
3. Connect Shopify
Connect the Shopify store whose prices you want compared with your price sheet (Settings → Integrations → Shopify).
4. Connect Slack
Connect the Slack workspace for the report (Settings → Integrations → Slack).
5. Pick your price sheet
Open “Read your price sheet” and pick the account, spreadsheet and tab (SKU | Product | Price).
| Setting | What to enter | In step |
|---|---|---|
| Google account (Price sheet) | The Google account that can open the spreadsheet. Pick your connected Google Sheets account. | “Read your price sheet” |
| Price sheet spreadsheet | Paste the link of the spreadsheet. | “Read your price sheet” |
| Price sheet tab | The tab with one row per product (SKU | Product | Price). | “Read your price sheet” |
6. Pick your Shopify store
Open “Read your Shopify products” and pick your store.
| Setting | What to enter | In step |
|---|---|---|
| Shopify store | The Shopify store to compare. Pick your connected Shopify account. | “Read your Shopify products” |
7. Slack and your notes
Open “Note what to check” and replace the placeholder, then pick the Slack account and channel on “Post the mismatches to Slack”.
| Setting | What to enter | In step |
|---|---|---|
| Differences that are on purpose | Replace the placeholder with your business, which price is the reference and any differences that are on purpose. It starts as “[YOUR BUSINESS, WHICH CHANNEL'S PRICE IS THE REFERENCE, AND PRICE DIFFERENCES THAT ARE ON PURPOSE (E.G. A STANDING DISCOUNT IN YOUR STORE)]” until you replace it. | “Note what to check” |
| Slack account | The Slack workspace for the report. Pick your connected Slack account. | “Post the mismatches to Slack” |
| Slack channel | Where mismatches are posted, e.g. #store. | “Post the mismatches to Slack” |
8. Test it with Dry Run
Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.
9. Switch the trigger on
Open the trigger, set your time zone and switch the schedule on. It runs every day at 8:00.
How it works
The agent is a normal workflow with 10 steps (1 AI step). You can open, edit and monitor it like any other workflow.
- Every day at 8:00 — Runs on a schedule (cron 0 8 * * *, UTC — change it in the trigger's settings). Compares your prices every morning. Set your time zone on the trigger.
- Read your price sheet — Google Sheets: Read rows. Reads your price sheet (SKU | Product | Price): the prices your website or price list uses.
- Read your Shopify products — Shopify: Find products. Reads up to 250 Shopify products with each variant's SKU and price.
- Compare the prices — Step. In code, not AI: groups every price by SKU (the same SKU on your price sheet and in Shopify), keeps SKUs found in both and lists the ones whose prices differ, biggest difference first.
- Note what to check — AI step (runs on your AI provider key). AI reads the mismatches (found in code) and writes a short note on what to check, without typing any prices.
- Any mismatches? — Step. In code: is there at least one SKU whose prices differ?
- Report? — Decision: picks the branch to follow. Mismatches: posted to Slack. Otherwise the run ends with nothing to report.
- All prices match — Kept in the run history. Branch: All match. Every SKU found on both your price sheet and Shopify has the same price.
- Post the mismatches to Slack — Slack: Post a message. Branch: Prices differ. Posts the SKUs whose prices differ, each channel's price (from code) and the AI's note.
- Reported — Kept in the run history. The run history keeps every comparison.
Test it with Dry Run
Press Dry Run in the canvas. The agent runs on the sample data stored on its trigger (the “Sample data for Dry Run” box), so you can check every step's output before anything is live.
- Nothing is sent or written: app actions, emails and Slack posts are simulated, and AI steps don't call your AI provider.
Go live
- Open the trigger, set your time zone and switch the schedule on. It runs every day at 8:00.
- Scheduled runs start only once the schedule is activated, and can't repeat faster than your plan's minimum interval.
- The setup checklist adds a “paid plan” item before activation: live runs need a paid plan (the Free plan only runs Dry Runs).
- When every checklist item is done and the trigger is on, the checklist says “Live — this agent is running”. Follow its runs in the workflow's History tab and in Analytics → Agents.
Questions
How are products matched?
By SKU, in code: the SKU column of your price sheet and each Shopify variant's SKU (ignoring upper and lower case). Products without a SKU aren't compared.
What about eBay and Amazon?
Not in this agent: our eBay connection reads inventory without prices, and our Amazon connection reads orders and stock, not your listing prices. Add those prices to your price sheet to compare them by hand.
Will it fix the prices?
No. It only reports. You decide which price is right and change it yourself.
Troubleshooting
- “No AI provider connected” or a rejected key: connect or fix the key in Settings → AI Providers, then press Test there.
- A checklist item stays unticked: the setting is still empty or still contains its placeholder text. Open the step from the checklist and fill it in.
- An app step fails with “Needs reconnect”: the account's access was revoked or expired. Reconnect it in Settings → Integrations.
- Slack says the app isn't in the channel: in Slack, type /invite @Fluxo Flow in that channel (always needed for private channels).
- It didn't run at the expected time: the schedule must be activated, and its time is in the trigger's timezone.
- A step failed: open the run in History and check that step in the Trace tab for the error and what it received.
Generated from the agent's own workflow, so it always matches what the agent does. Last updated .