Ah, Instinct as in instinct.co, got it. Honest answer: for most restaurants, a general assistant is plenty. Booking is a one-shot errand, and it sounds great at errands. The impossible tables are a different game. They release on fixed venue-specific schedules (one famous room drops 52 to 65 tables at 5:00pm Pacific, daily) and the desirable ones vanish in about 3 minutes. Winning that isn't "try to book when asked." It's standing vigil at machine cadence for weeks, knowing each venue's clock, and striking inside a 3-minute window at 5:01pm on a Tuesday when nobody asked you anything. That's a standing specialist service, not an errand. Honestly, the two compose: an assistant like Instinct should be able to take "get me into X" and hand the vigil to something like this. So: better for the tables you can't get, overkill for the ones you can.
I run a small system that watches availability at hard-to-book restaurants at ~90-second resolution. The first analysis produced a great stat: half of all new tables in one hour of the day. Before publishing I broke it down per venue and per date, and it died: the spike was my own polling schedule reflected back at me at sparsely-watched venues. Two more "findings" died the same way (both were onboarding artifacts). What survived dense-cadence filtering was better: individual restaurants release tables on fixed daily clocks, like one famous restaurant dropping 52 to 65 tables at 5:00pm Pacific every single day. Happy to answer questions about the measurement traps; the instrument-artifact stuff was the humbling part.
been using instinct for this recently. Will this be better?
Ah, Instinct as in instinct.co, got it. Honest answer: for most restaurants, a general assistant is plenty. Booking is a one-shot errand, and it sounds great at errands. The impossible tables are a different game. They release on fixed venue-specific schedules (one famous room drops 52 to 65 tables at 5:00pm Pacific, daily) and the desirable ones vanish in about 3 minutes. Winning that isn't "try to book when asked." It's standing vigil at machine cadence for weeks, knowing each venue's clock, and striking inside a 3-minute window at 5:01pm on a Tuesday when nobody asked you anything. That's a standing specialist service, not an errand. Honestly, the two compose: an assistant like Instinct should be able to take "get me into X" and hand the vigil to something like this. So: better for the tables you can't get, overkill for the ones you can.
good point but hahaha this does sound very AI
whos this actually for? , your icp to be precise What would make the next 90 days a success for you?
Hotel concierges would be ideal, but consumers are likely avid users.
I run a small system that watches availability at hard-to-book restaurants at ~90-second resolution. The first analysis produced a great stat: half of all new tables in one hour of the day. Before publishing I broke it down per venue and per date, and it died: the spike was my own polling schedule reflected back at me at sparsely-watched venues. Two more "findings" died the same way (both were onboarding artifacts). What survived dense-cadence filtering was better: individual restaurants release tables on fixed daily clocks, like one famous restaurant dropping 52 to 65 tables at 5:00pm Pacific every single day. Happy to answer questions about the measurement traps; the instrument-artifact stuff was the humbling part.