admin
f7ad9ba51f
- 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
32 lines
890 B
JSON
32 lines
890 B
JSON
{
|
|
"facts": [],
|
|
"decisions": [
|
|
{
|
|
"decision": "The substantive decision is deferred until more information is available.",
|
|
"evidence": "Mira: Okay, let's not decide this today. Jonas: Agreed, we need more input."
|
|
}
|
|
],
|
|
"todos": [
|
|
{
|
|
"task": "Lea will bring Dana's feedback about the weekly dashboard next time.",
|
|
"responsible": "Lea",
|
|
"deadline": "next time",
|
|
"evidence": "Lea: I will bring Dana's feedback next time."
|
|
}
|
|
],
|
|
"questions": [],
|
|
"positions": [
|
|
{
|
|
"speaker": "Jonas",
|
|
"position": "Jonas prefers moving the weekly dashboard to Monday morning.",
|
|
"evidence": "Jonas: I would prefer moving it to Monday morning."
|
|
},
|
|
{
|
|
"speaker": "Lea",
|
|
"position": "Lea thinks Monday is difficult for support.",
|
|
"evidence": "Lea: Monday is rough for support."
|
|
}
|
|
],
|
|
"technical": []
|
|
}
|