Frequently asked questions

It reads the feedback people give you and groups what repeats into named insights, each with the exact words it was counted from underneath. The feedback comes from a short survey you embed on any page, or from what you already have: a Typeform export, Google reviews, a batch of support e-mails. Under ten complete responses it shows a count instead of a guess.

You can check every insight. It opens into the exact feedback it was counted from, nothing is named under ten complete responses, and a failed recalculation is shown as failed, never as a fresh result. Plenty of tools group feedback with AI now, some for free.

No. The closed question can be a rating, but there is no NPS dashboard and no score to watch. The product is built around what people write and what repeats in it.

No. It doesn't ask for reviews or publish them, and nothing written here appears on your site. You can import reviews you already have, from Google Play or Google reviews, to see what repeats in them.

No. It does not try to answer "where did you hear about us"; other tools do that well and this one stays out of it.

No. It never sees your sales or traffic, so it will not claim to have moved a number it cannot see.

No. The default survey is one tap and one short follow-up, not a panel study with screening, quotas and multiple waves.

Open it. Every insight lists the feedback it was counted from, word for word, and each quote shows the source and the question it came from. The only text in that view nobody wrote to you is the insight's name and description, and both are labelled as generated.

There are fewer than ten complete responses in the period you're looking at, counted across every source in the project. An imported review, e-mail or spreadsheet row counts as one, the same as one finished survey. Below ten, the app shows how many you have and how many are missing, with a link to the raw feedback, instead of naming insights from a handful of replies.

The panel says the run failed, shows the last successful result together with the date it was calculated, and offers to try again. It never shows insights without a calculation date and never presents an old result as a new one. Your answer list keeps working.

A language model, and they are labelled as generated. Every quote under an insight is someone's own words, from a survey or from feedback you brought in. Grouping is the only step a model is involved in: counting, matching and the arithmetic behind every number are ordinary code. Nothing is filtered out along the way, so everything you collected or imported stays in the list and in the counters.

If you already have ten or more pieces of feedback dated this month, or with no date, import them and they are counted at the next automatic refresh. With a survey alone, it depends on how many people see it and finish it. Your panel shows the real count from day one.

Yes. Upload a CSV, Excel or JSON file, paste text, or send it through the API, and it's analyzed together with your surveys under the same rules: quotes under every insight, and nothing named under ten complete responses. You don't need a survey at all; a project can hold only imported feedback.

Google Forms, Typeform, Tally, Google Play reviews and Google reviews of your business (from Google Takeout) are recognised and mapped for you. Any other spreadsheet, as CSV or Excel, works too: you pick the column with the text. A form with several open questions goes into a survey with the same questions, so each answer keeps its question.

Yes. Everything in a project is read as one set and grouped by meaning, so the same complaint in a Google review and in a survey lands in one insight. Each insight shows how much of it comes from each source, and filtering by a source only narrows what you see.

It keeps its date. Feedback from this week and month is counted with everything else, and an earlier month is counted when you recompute it by hand, on Basic and Pro. Until then, that month shows how many items it hasn't counted yet. On Free, only feedback from the current week and month is analyzed.

Yes, through our API, on Basic and Pro. Add an HTTP step in n8n or Make, or a Webhooks by Zapier step (a paid Zapier feature), and send each new e-mail, chat or review to your source. This is also the way in for App Store Connect reviews and Intercom chats, which don't export their text to a file.

Up to your plan's limit per import, by file, paste or API, as listed on the pricing page. Each item counts toward your plan's monthly responses. If an import goes over either limit, it is refused as a whole and nothing is saved; a large file can be split and imported in parts.

Usually one per item: an item uses 1 AO per started 1,000 characters (what counts as one AO), and most reviews and form answers are shorter than that. A long support e-mail thread can use 2 or 3. The preview shows the exact number before you confirm, and if your monthly pool runs short, analysis covers what it can and the other items stay in your responses.

No. Survey answers and imported feedback go to our AI provider only to be grouped, and the provider doesn't train on them either; the privacy policy has the details.

Only the feedback text, with its question or the source's description as context, and no identifiers, account name or e-mail address. Before it leaves, our own server masks the personal details it can detect; this doesn't catch everything, and names are not masked, as the security page explains.

Yes, if you have the right to use it this way: you decide what you bring in, and you're responsible for it. We process it only on your behalf, as set out in the Terms.

No, and we will not call it that. The widget never asks a respondent for personal data, but each answer is tied to the visit it came from, which is what lets you open an answer in context. Calling it anonymous would be easier and untrue.

For your plan's storage period, shown on the pricing page; for imported feedback it counts from the day you import it. You can delete an item, a source or your whole account at any time, and the privacy policy says what happens next.

No. There is no industry benchmark and no cross-account comparison anywhere in the product, and there will not be one. We count how many accounts use a feature; your answers are never put next to somebody else's.

No. The script loads asynchronously and never blocks your page from rendering. If it fails to load, or our servers are unreachable, it simply does not appear — no broken layout, no error message, nothing for a visitor to notice.

Minutes. You pick a template, the wizard has at most three steps, and you can finish it without typing a single character, because the default questions are ready to publish. You can rewrite them afterwards and change them later without starting over.

By default: one closed question answered with a single tap, then one short written follow-up chosen by what they tapped. Nothing else in that default template: no email field, no discount, no newsletter sign-up. All answers are sent together in one request when the respondent finishes; closing the tab before that sends nothing.

Any page where you can add one script tag: your own site, a landing page, a web app, a documentation site. Where you can't add a script, send the survey's link in an e-mail or a message, or import the feedback you collect elsewhere.

By limits. Each plan includes everything in the plan below it: Free runs 1 survey with 100 responses a month, Basic 5 surveys with 5,000, Pro 50 surveys with 100,000. Seats, how many insights we recalculate per project, how often they refresh, and how long we keep your data all move up the same way. Recomputing insights by hand is on or off instead: Free does not include it, Basic and Pro do, and each run uses analyzed answers from the plan's monthly pool. Yearly billing is charged as ten months instead of twelve, so two months are free.

Businesses only, not individuals. You can buy from any country offered in the company details form in your account settings. Where that country needs a tax number, the form asks for it and we check it before you buy.

Most short answers use 1 AO. A longer answer uses one more for each further 1,000 characters.

No. All projects in your account share your plan's monthly pool of analyzed answers (AO). Adding a project doesn't add AO, and it doesn't use any either.