Trustpilot Review Monitor

Monitor Trustpilot reviews for any company and get alerted only when something actually changes: new reviews, rating drops, review-count jumps and vendor replies. Built for competitor review tracking — point it at your rivals, at your own listing, or at both, and send the result to Slack, a webhook, or an AI agent.

A scraper tells you what is on a review page. This Actor remembers what was there last time, so every run returns only the difference — plus a one-line verdict on whether it matters.

What it does

On its first run against a company, the monitor records the current state and returns a short confirmation of what it found — the current rating and review count — rather than replaying a year of history into a freshly connected Slack channel. From then on, each run compares reality against that stored baseline and emits only the differences.

It detects four kinds of change. A new review appears when a review ID shows up that was not there before. A reply is flagged when a company answers a review you had already seen, which is how you tell whether a competitor actually engages with unhappy customers. A rating move fires when the aggregate score shifts by more than a threshold you set, filtering out rounding noise. And a review count change catches bursts of activity even before individual reviews surface.

Because it is built on scraping rather than official partner APIs, it is not limited to whichever platforms have granted API access. New sources are added as adapters without changing anything else.

A verdict, not a data dump

Raw change rows leave the interpreting to you. Five one-star reviews about billing are a very different signal from five about downtime, so every run also produces a digest per company: how many reviews arrived and how negative they were, how far the rating moved, whether the volume is unusual compared to that company's own recent history, and which complaint themes dominate.

Notion: 6 new reviews averaging 2.5★, 3 negative; rating down 0.4 to 2.3.
Themes: payment, account, deleted, invoice. Volume 6.0x the usual.

Each digest carries a severity of none, low, medium or high, derived from stated thresholds rather than a black box — a rating drop past 0.3, three or more negative reviews, or negative reviews arriving during a volume spike.

This matters especially if an AI agent or automation is the consumer. Set outputMode to digest and the Actor returns one compact verdict per company instead of every row, so the agent gets an answer rather than a pile of text it has to re-read and reason over.

Why monitor competitors, not just yourself

Most reputation tools are built around managing your own listing, and treat competitor tracking as an afterthought. That is backwards for sales and product teams. A competitor collecting a wave of one-star reviews about a missing feature is a signal you can act on this week. A rating that quietly slides for two months is a market opening. This Actor treats every target the same way, so watching five competitors is exactly as easy as watching yourself.

How to use it

Add one line per company under What to watch, written as source:identifier — for example trustpilot:notion.so. A bare domain works too and defaults to Trustpilot. Run it once to establish the baseline, then schedule it hourly or daily; each run reports only what moved since the previous one.

To be told only about bad news, set Only alert on reviews at or below this rating to 2 and you will hear about one- and two-star reviews only. Paste a Slack incoming webhook URL to get a readable digest in the channel your team already watches, or a plain webhook URL to feed n8n, Make, your own backend or an AI agent with the raw JSON.

Input

The only required field is targets. Everything else has a sensible default. firstRun controls whether the first run stays silent or reports everything it finds. minScoreDelta sets how big a rating move has to be before it counts. maxReviewsPerCheck controls how deep each scan goes — reviews are read newest-first, so a shallow scan is normally enough and keeps the cost per check low. Raise it only if a target collects more reviews between two runs than the scan window.

State is kept in a named key-value store so it survives between runs. Use different stateStoreName values to keep separate watchlists apart, and resetBaseline to start over after changing what you monitor.

Output

Each detected change becomes one dataset row carrying the change type, the company, the full review where applicable, and before/after values for rating and count changes. You can download the dataset as JSON, CSV, Excel or HTML.

{
  "changeType": "new_review",
  "source": "trustpilot",
  "targetName": "Notion",
  "rating": 1,
  "title": "Charged after deleting my account",
  "publishedDate": "2026-08-04T10:13:26.000Z",
  "reviewUrl": "https://www.trustpilot.com/reviews/…",
  "detectedAt": "2026-08-07T12:47:37+00:00"
}

{
  "changeType": "score_changed",
  "targetName": "Notion",
  "previousValue": 2.5,
  "currentValue": 2.3,
  "delta": -0.2
}

Every run also writes a RUN_STATUS record to the key-value store, stating per target whether the check succeeded and why it did not. This matters more than it sounds: a monitor that silently returns "no changes" when its scraper is broken is worse than one that fails loudly, because an empty result reads as a fact and gets acted on. A failed read never overwrites a good baseline either, so a temporary outage cannot cause the next run to replay everything as new.

Cost

You pay per check performed and per change detected, not per monitored company. Watching many companies therefore does not multiply a subscription — a monitor that finds nothing on a quiet day costs almost nothing. Trustpilot needs no residential proxy, so monitoring runs on Apify's free tier.

Sources and roadmap

Trustpilot is supported today. G2 support is written and tested but waits on residential proxy access, since G2 hard-blocks datacenter IP addresses. Capterra and app store reviews follow the same adapter pattern.

Notes and support

The Actor reads publicly visible review pages only. Please make sure your use complies with the terms of the sites you monitor and with applicable data protection law, particularly if you store reviewer names. Found a bug or need another source? Open an issue on the Actor's Issues tab.