Track customer reviews across marketplaces and catch problems early

Every morning AI reads your product reviews from every marketplace and flags anything urgent before it goes viral.

How the work actually flows

It branches. Any that apply are taken; runs once per one per marketplace product.

Pattern: Multi-Choice (6) · Multiple Instances without Synchronization (12)

flowchart TD trig(["every morning schedule"]):::trigtime s0["check products across marketplaces"]:::task s1[["pull new reviews"]]:::mi s2["score review sentiment and urgency"]:::task s3["archive review with suggested reply"]:::task trig --> s0 s0 -->|"one per one per marketplace product"| s1 s1 --> s2 gx{"○ is the review critical"}:::gate s2 --> gx p00["send instant slack alert"]:::task gx -->|"critical review"| p00 p10["post daily brand score"]:::task gx -->|"daily summary"| p10 p00 --> s3 p10 --> s3 out[/"daily brand sentiment score posted"/]:::out pay{{"catch reputation risks early"}}:::pay s3 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepRuns once per itemAny that applyResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
E-commerce & ProductMessaging & NotificationsSpreadsheet & Database OpsWeb Scraping & Data Collection
Connects
MrScraperOpenAISlackNotionGoogle Sheets
Featured in

The problem it solves

Bad reviews show up across Tokopedia, Shopee, Amazon, and every other marketplace you sell on, but nobody has time to read them all every day. By the time someone notices a pattern of complaints, it's often already hurting your reputation.

Who it fits

E-commerce brands selling across multiple online marketplaces who need to catch reputation risks early.

How it works

  1. Every morning the system checks your list of products across marketplaces
  2. It finds and pulls new reviews, including ratings, photos, and reviewer details
  3. AI reads each review and scores sentiment, emotion, and how urgent it is
  4. Every review is archived in Notion, and a suggested customer service reply is generated
  5. Critical reviews trigger an instant Slack alert, and a daily brand score is posted to Slack
What you get

Review problems you catch before they spread

You see how customers feel about your products across every marketplace before issues escalate.

What you get

A daily brand sentiment score in Slack, an archived review history in Notion, and instant alerts on critical reviews.

What you need

A Notion account, a Slack workspace, an OpenAI API key, and a MrScraper account.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Back to the AI Playbook