The moment it happens

Score product reviews for sentiment and log them in Airtable

Every new product review is scored for sentiment, flagged if it looks fake, and saved to Airtable, with a weekly roundup in Slack.

Runs: The moment it happens
Apps: Airtable, Slack
AI: Yes, uses the built-in AI allowance
Access: Airtable read+write; Slack chat:write

Send this to your assistant

Create a ClickRuntime automation: when a new product review comes in, score its sentiment, flag it if it looks fake, save it to my Reviews table in Airtable and post a weekly summary to #product.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A small skincare brand collects reviews from its shop and a couple of marketplaces. The founder reads them in bursts, misses a run of complaints about a new pump bottle, and only spots the pattern when returns climb.

Scoring each review as it arrives and keeping them all in one table turns scattered comments into something the team can sort, filter and act on every week.

What you get out of it

Problems show up while they are small
A cluster of negative reviews about one product is visible in the table within days, not after a month of returns.
Suspicious reviews are set aside
Reviews that look fake are flagged so they do not skew how you read customer opinion, and you can report them to the marketplace.
Everyone sees the same weekly picture
A short Slack summary keeps product, support and marketing aligned without anyone exporting a report.
Reviews become data you can filter
With sentiment and product stored as fields, you can sort Airtable by product, score or date and find quotes for marketing.

How it works

What happens, step by step

Each time a review is posted, your shop or review tool sends it to ClickRuntime.
AI reads the review, scores it as positive, neutral or negative, and flags it if it looks fake.
The review and its scores are saved as a new record in your Airtable Reviews table.
Once a week a summary of the reviews is posted in your #product Slack channel.

Before it runs live

Connect Airtable
Connect Slack, then invite the app to the channel (type /invite @ClickRuntime there)
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Score product reviews for sentiment and log them in Airtablejust nowSucceeded

Slack · #productThis week: 42 reviews. Hydra Serum 88% positive. Northwind Night Cream: 5 negative, mostly about the pump bottle. 2 flagged as likely fake.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Google Sheets
Combine it with other Airtable and Slack steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

review_analysis_in_airtable_with_slack_summaries.pyexample

from clickruntime import on_event, credentials, http, ai, notify

URL = "https://api.airtable.com/v0/appXXXXXXXXXXXXXX/Reviews"
SCHEMA = {"type": "object", "properties": {"sentiment": {"type": "string", "enum": ["positive", "neutral", "negative"]},
          "likely_fake": {"type": "boolean"}, "topic": {"type": "string"}}, "required": ["sentiment", "likely_fake", "topic"]}

@on_event
def handle(event):
    r = event.json or {}
    text = (r.get("text") or "")[:3000]
    res = ai.generate(f"Product: {r.get('product')}\nRating: {r.get('rating')}\nReview: {text}\n"
                      "Give sentiment, whether it looks fake, and a 3-word topic.", json_schema=SCHEMA, max_output_tokens=80).json
    key = credentials.secret("AIRTABLE_API_KEY")
    http.post(URL, headers={"Authorization": f"Bearer {key}"}, json={"fields": {
        "Product": r.get("product"), "Rating": r.get("rating"), "Review": text, "Sentiment": res["sentiment"],
        "Likely fake": res["likely_fake"], "Topic": res["topic"], "Received": event.received_at}})
    if res["sentiment"] == "negative" and not res["likely_fake"]:
        notify.slack(f"Negative review of {r.get('product')}: {text[:200]}", channel="#product")
    return res

FAQ

Common questions

Where do the reviews come from?

Any shop, form or review tool that can send a webhook when a review is posted. Each one sends the review text, rating and product to your trigger link.

What makes a review look fake?

Signs such as generic praise with no product detail, mismatched rating and text, or wording copied from the product page. A flag is a prompt to check, not a verdict.

What is in the weekly summary?

The number of reviews per product, the share that were positive or negative, and the main complaints and praise in a few lines.

What permissions does it need?

Airtable read+write; Slack chat:write. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens