Card: the quickstart shows what this model answers

README.md

@@ -161,7 +161,7 @@ print(model.choice(
     },
     instructions="What is the customer's message about?",
 ))
-# {"type": "choice", "choice": "card_delivery", "confidence": ..., "probabilities": {...}}
+# What this model answers here: "card_delivery", probability 0.999, confidence 0.979
 ```
 
 `noul` and `score` work the same way (`model.noul(...)`, `model.score(...)`); `model.predict([...])` answers a batch. This is the base model, before any training on your data: for your own decision, train it on [typestrict.ai](https://typestrict.ai).