Skip to content

Weekly

Get a weekly digest of what reviewers say

Every Monday you see last week's reviews sorted into themes and moods, with the harshest ones quoted.

Runs
Weekly
Apps
Trustpilot
AI
Yes, uses the built-in AI allowance
Access
apikey (public)

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, take last week's Trustpilot reviews, group them by sentiment and topic such as delivery, price and support, and email me the summary with the three worst reviews quoted.

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

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

Why use it

Why teams use this automation

A business with hundreds of Trustpilot reviews cannot read each one carefully. The owner skims the stars, notices the average is 4.2 and stops there, while the same complaint about slow delivery appears fourteen times in the last month. By the time anyone connects the dots, the pattern has cost sales and a lower score.

Every week, this collects reviews posted since the last run and passes them to an AI step that identifies the main themes people praise and complain about, with the overall sentiment. The summary arrives by email, so you read one page instead of dozens of reviews.

Customer experience leads and founders use it to decide what to fix first. The goal is to turn a pile of reviews into a short list of things worth acting on, so patterns are caught while they are small and cheap to fix.

What you get out of it

  • Complaints are grouped into themes

    Fourteen reviews about late delivery become one line in the email. Seeing a repeated problem named and counted gets it onto the agenda, where scattered individual reviews would be shrugged off.

  • Praise you can reuse

    The summary shows what customers love, such as friendly support or fast setup. That tells marketing which strengths to highlight and tells the team which habits to protect. Marketing can then use real customer phrases.

  • Reading time drops sharply

    Reading a week of reviews can take an hour. A one-page summary takes two minutes, so the review trends get looked at weekly rather than being skipped because nobody has the time.

  • Earlier warning of declines

    A change in sentiment from one week to the next shows up before the star average moves. You can respond to a product or service issue while only a handful of customers are affected.

  • Evidence for decisions

    When you argue for a fix, a weekly theme summary backs it up with real customer words. It is easier to win budget for a change that customers are visibly asking for.

How it works

What happens, step by step

  1. Every Monday, ClickRuntime collects the Trustpilot reviews posted in the past 7 days.

  2. AI reads them, sorts each into positive, neutral or negative, and groups them by theme such as delivery or support.

  3. You get an email with the mood counts, each theme with what reviewers said, and quotes from the harshest reviews.

Before it runs live

  • Connect Trustpilot

What you get

RunsWeekly
Get a weekly digest of what reviewers saytoday, 9:00Succeeded
Email · Trustpilot weeklyPositive 31 · Neutral 4 · Negative 6 Delivery: 9 (5 negative, mostly late parcels) · Support: 7 (all positive)

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

  • Run it at a different time, more or less often, or only on weekdays
  • Change what the AI looks for, or how it writes the result
  • Add another app, for example also send it to Slack
  • Combine it with other Trustpilot 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.
ai_sentiment_digest_of_new_reviews.pyexample
from datetime import datetime, timedelta, timezone
from clickruntime import on_trigger, credentials, http, ai, notify

BUSINESS_UNIT_ID = "your-business-unit-id"

@on_trigger
def run(event):
    since = (datetime.now(timezone.utc) - timedelta(days=7)).isoformat()
    reviews = http.get(f"https://api.trustpilot.com/v1/business-units/{BUSINESS_UNIT_ID}/reviews",
                       params={"apikey": credentials.secret("TRUSTPILOT_API_KEY"), "perPage": 100,
                               "orderBy": "createdat.desc"}).json()["reviews"]
    week = [r for r in reviews if r["createdAt"] >= since[:19]]
    if not week:
        return {"reviews": 0}
    lines = "\n".join(f"{i}. {r['stars']}★ {r['title']}: {r['text'][:400]}" for i, r in enumerate(week, 1))
    summary = ai.generate(lines, max_output_tokens=900,
                          system="Group these reviews by sentiment and by topic (delivery, price, support, product, other) "
                                 "with counts. Then quote the three worst reviews word for word.").text
    notify.email_me(f"Trustpilot: {len(week)} reviews last week", summary)
    return {"reviews": len(week)}

FAQ

Common questions

Does the AI read the full text of each review?
Yes. It receives the review title, text and star rating for the reviews in that week. It does not see any private customer data beyond what is already public on the review page. Only public review content is used.
What if there were no new reviews this week?
The run finds nothing to summarize, so the email will say no new reviews were found or be skipped, depending on your preference. Low-volume businesses sometimes choose a monthly schedule instead. Slow weeks simply produce a shorter note.
Can it pick out reviews that need a reply?
You can add that to the instructions, so the summary lists reviews that mention refunds, safety or legal issues for follow-up. It will flag them, but replying on Trustpilot remains something you do yourself. The reply itself stays with a person.
What permissions does it need?
apikey (public). 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 each time it runs (weekly). Checks that find nothing to do and stop right away aren't counted.
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.

Set up “Get a weekly digest of what reviewers say” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.