EXAMPLEIllustrative example · fictional restaurant «Sazón de Origen». Not your data: your result is built with YOUR restaurant's.See the assistant →
Sazón de OrigenFictional contemporary Colombian restaurant in Medellín, 2 locations, 6 years in business. Every sample result in the library comes from this same case.
Reviews, Reputation and Automated Messaging

Sample result

Recurring Problem Detector for Restaurant Reviews

The owner asked this:«I have 58 reviews from the last three months across Google and the delivery app. I know something is off with weekend service, but every time I read them I am left with the last one that stung.»

① The cleaned lot and the count with its weight

Block A — the lot: 58 read · a 90-day period · Google 39 and delivery app 19 · 14 with no problem named (they join the mute pile) · 4 discarded with their reason: two wanted a dish the house does not sell, one had no visit, and one from the Sunday when lunch broke on a local public holiday in the market's calendar.

Block B — the count, sorted by weight and not by appearances:

ProblemAppearances% of those namingHarmWeightStationSlot and location
Dish arrives cold512.5%315PackagingEvening · delivery · Centro
Wait at the table with no warning922.5%19FloorSaturday evening · Centro
Portion smaller than expected410%28KitchenAll day · both locations
Unexplained service charge25%24Price— · Norte

The bottom one does not enter: the service charge stays on the watch list with its figure —2 appearances out of 40 do not reach the threshold— and gets re-read at the second count. Not the bin: the list.

② The finding: where frequency and harm do NOT agree

The wait shows up 9 times and the cold plate 5, but the cold plate weighs nearly double. That is the only line in this report that justifies the work: whoever fixes the wait first will be buying chairs while the kitchen loses guests.

And the wait is not born where it looks. Crossing the order time against Saturday's occupancy, all nine complaints fall in the busiest slot with the same pass time as the rest of the week: it is table turnover, not the kitchen. The fix belongs to the floor —telling guests the wait when seating them— and costs nothing.

SUPUESTO: harm is weighed on the house's declared scale (1 returns, 2 returns less, 3 never returns), not on an industry figure for how many guests are lost per review, which shifts by market and by channel. If the real harm of the short portion were 3 and not 2, its weight becomes 12 and it overtakes the wait: the order of the plan changes, and that is why the assumption is written down and not hidden.

The full example has 1 more part(s): you see them inside the library, with your account.