Grokking LLM Evals
Vote

0% completed

​

What a Test Case Contains

{ "id": "jt-0147", "input": { "request": "Our furnace stopped last night and it is 15 degrees outside. The house is getting colder." }, "context": {"address_on_account": false, "home_type": "house"}, "expected": { "trade": "heating_and_cooling", "urgency": "emergency", "properties": [ "reply asks for the address", "reply promises no arrival time or price", "summary adds no detail the customer did not give" ] }, "tags": {"style": "short", "missing_info": "address", "danger_wording": "explicit"},

.....

.....

.....

Like the course? Get enrolled and start learning!

Reading Progress

0%


Vote for new content