- 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
23 lines
608 B
JSON
23 lines
608 B
JSON
{
|
|
"facts": [
|
|
{
|
|
"fact": "The customer export takes longer than Paula expected.",
|
|
"evidence": "Paula: The customer export takes longer than I expected."
|
|
},
|
|
{
|
|
"fact": "There is no owner for the customer export issue for now.",
|
|
"evidence": "Paula: Right, no owner for now."
|
|
}
|
|
],
|
|
"decisions": [
|
|
{
|
|
"decision": "The customer export issue will stay on the risk list for now.",
|
|
"evidence": "Sam: Then let's just keep it on the risk list. Paula: Right, no owner for now."
|
|
}
|
|
],
|
|
"todos": [],
|
|
"questions": [],
|
|
"positions": [],
|
|
"technical": []
|
|
}
|