Restaurant SMS host

Guests text the restaurant. The model reads intent and spots the allergy that has to reach the kitchen; party size and free seats come from the booking system.

  • An allergy always reaches the kitchen
  • Capacity comes from your system, not the model
  • Unsure about intent? A host answers

A request comes in

Pick a scenario or write your own. The facts on the right come from your systems.

From your systems · never sent to the model

The model answers the policy's questions

You play the model: drag an answer and watch the decision change.

intentWhat does the guest want from message?

severe-allergy?Does message mention a serious allergy or medical diet?

The policy decides

Plain code picks the branch, and says which clause and which readings did it.

Pick a scenario to see the decision.

Call it from your code

The same route, the same answer. Drop the answers to let the model reply.

shell
curl https://jevlang.sh/api/reservation \
  -H 'content-type: application/json' \
  -d '{"input":{"message":"Hi! Table for 4 Saturday 7pm? My son carries an EpiPen for tree nuts.","partySize":4,"seatsFree":12},"answers":{"intent":{"choice":"book","confidence":0.97},"severe-allergy?":{"noul":0.96}}}'