- introduce Gold Standard evaluation corpus - document decision taxonomy - define prompt-engineering methodology - add regression workflow - establish Prompt Version 2 baseline - validate decision_simple, decision_deferred and decision_none
14 lines
328 B
JSON
14 lines
328 B
JSON
{
|
|
"facts": [],
|
|
"decisions": [
|
|
{
|
|
"decision": "The welcome email will be sent after account activation.",
|
|
"evidence": "So are we agreed that the welcome email moves to after activation? Ben: Agreed. Cara: Yes, let's do that."
|
|
}
|
|
],
|
|
"todos": [],
|
|
"questions": [],
|
|
"positions": [],
|
|
"technical": []
|
|
}
|