- 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
25 lines
673 B
JSON
25 lines
673 B
JSON
{
|
|
"facts": [],
|
|
"decisions": [],
|
|
"todos": [],
|
|
"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": "Mira",
|
|
"position": "Mira thinks Tuesday might work better for support.",
|
|
"evidence": "Mira: Tuesday might work better for support."
|
|
},
|
|
{
|
|
"speaker": "Lea",
|
|
"position": "Lea suggests keeping Friday and making the dashboard shorter.",
|
|
"evidence": "Lea: Or we keep Friday and make the dashboard shorter."
|
|
}
|
|
],
|
|
"technical": []
|
|
}
|