This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Hunch
AI formulas that score, tag and classify any text column
Every row gets a number you can sort. =HUNCH(A2, "Is this lead a decision maker?") returns a probability. HUNCHPICK picks one option from your list, HUNCHSCORE places the text on your scale, HUNCHMULTI answers several yes/no questions per row at once. Drag it down, then sort, filter and color as usual. Works in Google Sheets and Excel with one key. 100 rows free, then $29 for 5,000. No subscription, credits never expire. Powered by Jev, TypeSafe's judgment model.
Hi, I am the one person behind this.
Hunch started with a spreadsheet problem, not an AI idea. A column of lead notes, a question about each row, and the only options were reading 2,000 rows or pasting them into a chat window and parsing paragraphs back into cells.
So it is four formulas:
=HUNCH(text, question) gives the probability that the answer is yes, 0 to 1.
=HUNCHPICK(text, "a|b|c") gives one option from your list.
=HUNCHSCORE(text, question, "low|mid|high") gives a position on levels you define.
=HUNCHMULTI(range, "q1|q2|q3") answers several yes/no questions per row in one go, one column each.
Point any of them at a range and the whole column fills in one request per 40 rows. Then you sort, filter and color like any other column. Same formulas in Excel (=HUNCH.ASK and friends), same key.
Under the hood the answers come from Jev, TypeSafe's System One model. It returns a calibrated judgment rather than generated text, which is what lets me promise a number per row and charge per row: 100 rows free, $29 for 5,000 rows, $19 for 25,000 more, credits never expire, no subscription. Blanks, duplicates and recalculation within six hours are free.
Honest limits: it judges text. It does not do arithmetic, counting or date comparison. English works best.
It launched this month and I have no customers to quote, so the demo sheets carry real rows and real model outputs instead. Copy the template, the two demo tabs already show the outputs, and the form on the site sends you 100 rows free to try on your own data before paying.
I will be here all day. Ask me anything, including the awkward questions about accuracy and data.
No comment highlights available yet. Please check back later!
About Hunch on Product Hunt
“AI formulas that score, tag and classify any text column”
Hunch was submitted on Product Hunt and earned 17 upvotes and 1 comments, placing #37 on the daily leaderboard. Every row gets a number you can sort. =HUNCH(A2, "Is this lead a decision maker?") returns a probability. HUNCHPICK picks one option from your list, HUNCHSCORE places the text on your scale, HUNCHMULTI answers several yes/no questions per row at once. Drag it down, then sort, filter and color as usual. Works in Google Sheets and Excel with one key. 100 rows free, then $29 for 5,000. No subscription, credits never expire. Powered by Jev, TypeSafe's judgment model.
Hunch was featured in Productivity (661.9k followers), Spreadsheets (9.9k followers) and Artificial Intelligence (479.9k followers) on Product Hunt. Together, these topics include over 290.9k products, making this a competitive space to launch in.
Who hunted Hunch?
Hunch was hunted by Edoardo Panichi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Hunch stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Edoardo Panichi